Lineage Analysis of CRISPR and shRNA Screens

Analysis of the Broad’s Avana CRISPR (Broad Institute Cancer Dependency Map 2018, Meyers et al. 2017) and the Broad and Dana-Farber Cancer Institite’s Achilles shRNA (MacFarland et al. 2018, Data Science 2018).

The Avana screen produced results using CERES (Meyers et al. 2017) (GitHub), which generates gene dependency scores from sgRNA depletion scores from gene essentiality screens and eliminates bias arising from the effect of copy number variation on Cas9 DNA cleavage. The lower the CERES score, the higher the likelihood that the gene is essential in the associated cell line. Scores are scaled per cell line such that a score of 0 is the median effect of nonessential genes and -1 is the median effect of common core essential genes.

In a previous version of the shRNA screen, DEMETER (GitHub) was used to compute a dependency score for each gene by using the depletion values from each shRNA to infer the effect of target knockdown (on-target) and of expressing a given miRNA seed (off-target) in each cell line. More negative values indicate increased dependency, while more positive values indicate lower dependency. Zero represents the avergae dependency across all cell lines.

In the new data release, DEMETER2 (GitHub repository), developed by McFarland et al. (2018) was used to analyze the Achilles screen. DEMETER2 expands on DEMETER by including parameters for cell-line-specific screen effects and noisy data, correcting for global differences in shRNA levels across cell lines, pooling data acorss cell lines via hierarchical modeling, and using Bayesian inference to compute uncertainty estimates. Now, a score of zero represents no dependency.

All annotation files (copy number, mutation status, and gene expression) (Consortium and Consortium 2015, Barretina et al. 2012) were downloaded from the DepMap Data Portal.

1 Set up

---

Load libraries.

library(NMF)
library(ggpubr)
library(ggsignif)
library(rowr)
library(data.table)
library(CePa)
library(plyr)
library(tidyverse)
library(magrittr)
library(matrixStats)
library(parallel)
library(kableExtra)
library(gridExtra)
library(broom)
library(glmnet)
library(devtools)
library(reshape2)
library(caret)
library(bsselectR)
library(ComplexHeatmap)
library(circlize)

2 Functions

---

2.1 Significance thresholding

adj_signif <- function(df) {
  # Takes df from compare_means and creates a signif code column for adjusted p-vals
  df$p.signif <- ifelse(df$p.signif == "ns", NA, df$p.signif)
  df$p.signif.adj <- ifelse(df$p.adj <= 0.0001, "****",
                     ifelse(df$p.adj <= 0.001, "***",
                     ifelse(df$p.adj <= 0.01, "**",
                     ifelse(df$p.adj <= 0.05, "*", NA))))
  df$p.short <- formatC(df$p, format = "g", digits =  2)
  df$p.adj.short <- formatC(df$p.adj, format = "g", digits =  2)
  
  return(df)
}

2.2 Make CRISPR grobs

makeCRISPRgrob <- function(g) {
  
  gene <- filter(crispr_data, Hugo_Symbol == g)
  
  # Mutation status
  crispr_color <- as.character(gene$Color)
  names(crispr_color) <- gene$Mutation_Status
  sig <- filter(crispr_signif, Hugo_Symbol == g)
  plot_mut <- ggplot(data = gene, aes(x = Mutation_Status, y = Score, color = Mutation_Status)) +
    geom_boxplot(outlier.shape = NA) +
    geom_jitter(alpha = 0.3, size = 0.7, position = position_jitter(w = 0.05)) +
    scale_color_manual(values = crispr_color) +
    geom_hline(yintercept = 0, linetype = 2, lwd = 0.3) +
    theme_light() +
    theme(legend.position = "none") +
    labs(x = paste0(g, " Mutation Status"), y = "CERES Score",
         title = "Mutation Status",
         subtitle = paste0("Wilcoxon test:\n- BH-corrected p-value: ", sig$p.adj.short, "\n- Uncorrected p-value: ", sig$p.short, "\nMutant lines harbor deleterious mutations."))
  
  # Copy number
  lo_cn <- range(gene$Copy_Number[!is.na(gene$Copy_Number)])[1]
  hi_cn <- range(gene$Copy_Number[!is.na(gene$Copy_Number)])[2]
  mid_cn <- (hi_cn - lo_cn) / 2
  plot_cn <- ggplot(data = gene, aes(x = Copy_Number, y = Score, color = Mutation_Status)) +
    geom_point(size = 0.5, alpha = 0.5) +
    geom_smooth(method = "lm", size = 0.5) +
    geom_hline(yintercept = 0, linetype = 2, lwd = 0.3) +
    scale_color_manual(values = crispr_color) +
    stat_cor(method = "pearson", show.legend = FALSE, label.x = c((lo_cn + mid_cn) / 2, (hi_cn - mid_cn) / 2 + mid_cn), label.y = max(gene$Score)) +
    theme(legend.position = "none") +
    labs(y = "CERES Score", color = "Mutation Status",
         x = paste0(g, " Theoretical Copy number"), title = "Copy Number",
         subtitle = "r: Pearson correlation coeffcient")
  
  # Gene expression
  lo_ge <- range(gene$RPKM_log2[!is.na(gene$RPKM_log2)])[1]
  hi_ge <- range(gene$RPKM_log2[!is.na(gene$RPKM_log2)])[2]
  mid_ge <- (hi_ge - lo_ge) / 2
  plot_ge <- ggplot(data = gene, aes(x = RPKM_log2, y = Score, color = Mutation_Status)) +
    geom_point(size = 0.5, alpha = 0.5) +
    geom_smooth(method = "lm", size = 0.5) +
    geom_hline(yintercept = 0, linetype = 2, lwd = 0.3) +
    scale_color_manual(values = crispr_color) +
    stat_cor(method = "pearson", show.legend = FALSE, label.x = c((lo_ge + mid_ge) / 2, (hi_ge - mid_ge) / 2 + mid_ge), label.y = max(gene$Score)) +
    theme(legend.position = "none") +
    labs(y = "CERES Score", color = "Mutation Status",
         x = paste0(g, " Gene Expression [log2(RPKM)]"),
         title = "Gene Expression",
         subtitle = "r: Pearson correlation coeffcient")
  
  # Cell line lineage
  plot_tissue <- ggplot(data = gene, aes(x = primary_tissue, y = Score, color = Mutation_Status)) +
    geom_point(alpha = 0.5) +
    scale_color_manual(values = crispr_color) +
    geom_hline(yintercept = 0, linetype = 2, lwd = 0.3) +
    scale_y_continuous(sec.axis = sec_axis(~ .)) +
    coord_flip() +
    theme(legend.position = "none") +
    labs(y = "CERES Score", x = "Primary Tissue",
         color = "Mutation Status", title = g)
  
  # Arrange plots
  plot <- ggarrange(ggarrange(plot_tissue, nrow = 1, labels = c("A")),
                    ggarrange(plot_mut, plot_cn, plot_ge, nrow = 3,
                              labels = c("B", "C", "D"), heights = c(2, 3, 3)),
                    font.label = list(size = 30, face = "bold"),
                    nrow = 1, ncol = 2, widths = c(3, 2))
  return(plot)
}

2.3 Make lineage plot

makeCRISPRlinplot <- function(g) {
  sig <- filter(crispr_signif_lineage, Hugo_Symbol == g)
  if(nrow(sig) == 0) {
    return(NULL)
  }
  else {
    gene <- filter(crispr_data, Hugo_Symbol == g)
    gene <- merge(gene, sig, by = c("Hugo_Symbol", "group_general_lineage_name"))
    gene <- mutate(gene, group_general_lineage_name = reorder(group_general_lineage_name, p, mean))
    crispr_color <- as.character(gene$Color)
    names(crispr_color) <- gene$Mutation_Status
    score_range <- abs(range(gene$Score)[2] - range(gene$Score)[1])
    round_accuracy <- ifelse(score_range <= 2, 0.25,
                             ifelse(score_range <= 3, 0.5, 1.0))
    
    plot <- ggplot(data = gene, aes(x = group_general_lineage_name, y = Score)) +
      geom_point(alpha = 0.5, mapping = aes(color = Mutation_Status)) +
      scale_color_manual(values = crispr_color) +
      coord_cartesian(y = c(min(gene$Score), round_any(x = max(gene$Score), accuracy = round_accuracy, f = ceiling))) +
      geom_signif(data = gene, mapping = aes(xmin = group_general_lineage_name, xmax = group_general_lineage_name, annotations = paste(p.short, "\n", p.adj.short), y_position = max(gene$Score)), manual = TRUE, tip_length   = 0, size = 0, textsize = 3) +
      theme(legend.position = "top", axis.text.x = element_text(angle = 70, hjust = 1, size = 10)) +
      labs(y = "CERES Score",
           x = "Lineage",
           color = "Mutation Status",
           title = paste0(g, ": CERES score by cell line lineage"),
           subtitle = "Lineages sorted by increasing p-value; labels indicate unadjusted p-value / BH-corrected p-value.\nMutant lines harbor deleterious mutations.")
    return(plot)
  }
}

2.4 Make tissue plot

makeCRISPRtissueplot <- function(g) {
  sig <- filter(crispr_signif_tissue, Hugo_Symbol == g)
  if(nrow(sig) == 0) {
    return(NULL)
  }
  else {
    gene <- filter(crispr_data, Hugo_Symbol == g)
    gene <- merge(gene, sig, by = c("Hugo_Symbol", "primary_tissue"))
    gene <- mutate(gene, primary_tissue = reorder(primary_tissue, p, mean))
    crispr_color <- as.character(gene$Color)
    names(crispr_color) <- gene$Mutation_Status
    score_range <- abs(range(gene$Score)[2] - range(gene$Score)[1])
    round_accuracy <- ifelse(score_range <= 2, 0.25,
                             ifelse(score_range <= 3, 0.5, 1.0))
    
    plot <- ggplot(data = gene, aes(x = primary_tissue, y = Score)) +
      geom_point(alpha = 0.5, mapping = aes(color = Mutation_Status)) +
      scale_color_manual(values = crispr_color) +
      coord_cartesian(y = c(min(gene$Score), round_any(x = max(gene$Score), accuracy = round_accuracy, f = ceiling))) +
      geom_signif(data = gene, mapping = aes(xmin = primary_tissue, xmax = primary_tissue, annotations = paste(p.short, "\n", p.adj.short), y_position = max(gene$Score)), manual = TRUE, tip_length   = 0, size = 0, textsize = 3) +
      theme(legend.position = "top", axis.text.x = element_text(angle = 70, hjust = 1, size = 10)) +
      labs(y = "CERES Score",
           x = "Primary Tissue",
           color = "Mutation Status",
           title = paste0(g, ": CERES score by cell line primary tissue"),
           subtitle = "Primary tissues sorted by increasing p-value; labels indicate unadjusted p-value / BH-corrected p-value.\nMutant lines harbor deleterious mutations.")
    return(plot)
  }
}

3 Data management

---

3.1 D. Charytonowicz cell line converter

This comprehensive cancer cell line information curated by Daniel Charytonowicz.

ccl_converter <- read.delim("./data_munging/cell_line_database_v1_20180911.tsv", row.names = 1, sep = "\t", header = TRUE)

3.2 DepMap cell line metadata

ccl_info <- read.delim("./data_munging/DepMap-2018q3-celllines.csv", sep = ",", header = TRUE, na.strings = c("", NA))
ccl_info$Primary.Disease <- gsub("\\\\", "", ccl_info$Primary.Disease)
ccl_info$Primary.Disease <- gsub("Ewings", "Ewing's", ccl_info$Primary.Disease)

# From figshare
crispr_meta <- read.delim("./data_munging/sample_info_18Q3_crispr.csv", sep = ",", header = TRUE, na.strings = c("", NA))
colnames(crispr_meta)[7] <- "CCLE_Name"

3.3 CGC gene list

Select genes from the Cancer Gene Census (CGC). The list was pulled from the International Cancer Genome Consortium (ICGC) data portal (Advaced Search > Genes > Curated Gene Set > Cancer Gene Census).

cgc <- data_frame("Hugo_Symbol" = read.delim("./data_munging/gene-ids-for-set-Cancer Gene Census.tsv", header = FALSE, sep = "\t")[, 2])

3.4 CCLE MAF file

For mutation calling, get paired gene name and cell line fields in a data frame. For this analysis, we don’t care about how many mutations there are per gene or what type of mutations there are, so I didn’t save more information. I took unique gene-cell line combinations since we only cared about mutation presence/absence. Add a Mutation_Status column denoting all entries in MAF files as mutations present in the associated cell lines.

maf_raw <- read.delim("./data_munging/CCLE_DepMap_18q3_maf_20180718.txt.gz", header = TRUE, sep = "\t")
# Filter for cell lines in CRISPR screen
maf_raw <- filter(maf_raw, Broad_ID %in% unique(crispr_meta$Broad_ID))
colnames(maf_raw)[colnames(maf_raw) == "Tumor_Sample_Barcode"] <- "CCLE_Name"

# Select columns
maf_df <- subset(maf_raw, select = c("Hugo_Symbol", "CCLE_Name", "Broad_ID", "Variant_Classification", "isDeleterious", "Reference_Allele"))
maf_df$Var_Length <- nchar(as.character(maf_df$Reference_Allele))

# Add Mutation_Status column
maf_df$Mutation_Status_Deleterious <- ifelse(maf_df$isDeleterious == TRUE, "Mutant", "Other")
maf_df$Mutation_Status_Nonsilent <- ifelse(maf_df$Variant_Classification == "Silent", "Other", "Mutant")
maf_df$Mutation_Status_DeleteriousMissense <- ifelse(maf_df$isDeleterious == TRUE | maf_df$Variant_Classification == "Missense_Mutation", "Mutant", "Other")
maf_df <- unique(subset(maf_df, select = c("Hugo_Symbol", "CCLE_Name", "Broad_ID", "Mutation_Status_Deleterious", "Mutation_Status_Nonsilent", "Mutation_Status_DeleteriousMissense", "Var_Length")))

# Whole MAF summary table
maf_summ <- maf_raw[, c("Variant_Classification", "isDeleterious")] %>% group_by(Variant_Classification, isDeleterious) %>% tally()
maf_summ$Percent <- format(round(maf_summ$n / sum(maf_summ$n) * 100, 4), nsmall = 2)
maf_summ$isDeleterious <- ifelse(maf_summ$isDeleterious == "TRUE", "Yes", "No")

knitr::kable(maf_summ, caption = "Distribution of variant classifications in the MAF file") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive"))

Distribution of variant classifications in the MAF file

Variant_Classification	isDeleterious	n	Percent
3’UTR	No	1	0.0003
3’UTR	Yes	30	0.0084
5’Flank	No	8	0.0022
5’Flank	Yes	34	0.0095
5’UTR	No	2	0.0006
5’UTR	Yes	15	0.0042
De_novo_Start_OutOfFrame	Yes	2006	0.5595
Frame_Shift_Del	Yes	12441	3.4698
Frame_Shift_Ins	Yes	9215	2.5701
IGR	No	6	0.0017
IGR	Yes	44	0.0123
In_Frame_Del	No	1747	0.4872
In_Frame_Ins	No	442	0.1233
Intron	No	9	0.0025
Intron	Yes	187	0.0522
Missense_Mutation	No	211359	58.9484
Nonsense_Mutation	Yes	12711	3.5451
Nonstop_Mutation	Yes	335	0.0934
Silent	No	94225	26.2795
Splice_Site	Yes	13180	3.6759
Start_Codon_Del	Yes	25	0.0070
Start_Codon_Ins	Yes	33	0.0092
Start_Codon_SNP	No	402	0.1121
Stop_Codon_Del	No	1	0.0003
Stop_Codon_Del	Yes	52	0.0145
Stop_Codon_Ins	Yes	39	0.0109

max(nchar(as.character(maf_raw$Reference_Allele)))
maf_raw %>% group_by(Variant_Type, isTCGAhotspot) %>% tally()

test <- filter(maf_raw, Hugo_Symbol == "KRAS")
test %>% group_by(isDeleterious) %>% tally()

3.5 CCLE copy number file

cn <- read.delim("./data_munging/public_18Q3_gene_cn.csv.gz", sep = ",", check.names = FALSE, header = TRUE)

# Convert log2 ratios (log2(CN/2)) to CN
cn[2:ncol(cn)] <- lapply(cn[2:ncol(cn)], function(x) 2 * (2 ^ x))

# Remove Entrez gene IDs from colnames
colnames(cn) <- gsub(" .*", "", colnames(cn))
colnames(cn)[1] <- "Broad_ID"

# Melt
cn_melt <- melt(data = cn, id.vars = "Broad_ID", measure.vars = colnames(cn[2:ncol(cn)]), variable.name = "Hugo_Symbol", value.name = "Copy_Number")

saveRDS(cn_melt, "./data_munging/rds/cn_melt_18Q3.rds", compress = "xz")

cn_melt <- readRDS("./data_munging/rds/cn_melt_18Q3.rds")

3.6 CCLE gene expression file

Gene expression data (Reads Per Kilobase of transcript, per Million mapped reads, RPKM).

ge <- read.delim("./../crispr_lineages_giant_files/CCLE_DepMap_18q3_RNAseq_RPKM_20180718.gct.gz", skip = 2, header = TRUE, sep = "\t", check.names = FALSE)

# Edit columns
ge$Name <- NULL
colnames(ge)[1] <- "Hugo_Symbol"

# Melt
ge_melt <- melt(data = ge, id.vars = "Hugo_Symbol", measure.vars = colnames(ge[2:ncol(ge)]), value.name = "RPKM")
## Split variable column
ge_melt <- with(ge_melt, cbind(Hugo_Symbol, colsplit(variable, pattern = " ", names = c("CCLE_Name", "Broad_ID")), RPKM))
## Remove parentheses around Broad IDs
ge_melt$Broad_ID <- gsub("\\(|\\)", "", ge_melt$Broad_ID)

saveRDS(ge_melt, "./../crispr_lineages_giant_files/ge_melt_18Q3.rds", compress = "xz")

ge_melt <- readRDS("./../crispr_lineages_giant_files/ge_melt_18Q3.rds")

3.7 DepMap dependency probabilities

dep <- read.delim("./data_munging/gene_dependency_18Q3.csv.gz", sep = ",", header  = TRUE, check.names = FALSE)
# Remove Entrez gene IDs from colnames
colnames(dep) <- gsub(" .*", "", colnames(dep))

3.8 Merge CRISPR data and annotations

The latest CRISPR CERES score data (18Q3, August 2018) was pulled from the DepMap Data Portal (Broad Institute Cancer Dependency Map 2018, Meyers et al. 2017).

crispr <- read.delim("./data_munging/gene_effect_18Q3.csv.gz", sep = ",", header  = TRUE, check.names = FALSE)
# Remove Entrez gene IDs from colnames
colnames(crispr) <- gsub(" .*", "", colnames(crispr))

Merge annotation data:

# Melt CRISPR dataset for merging
crispr_melt <- melt(crispr, id.vars = "Broad_ID", measure.vars = colnames(crispr)[2:ncol(crispr)], variable.name = "Hugo_Symbol", value.name = "Score")

# Melt dependency probabilities dataset for merging
dep_melt <- melt(dep, id.vars = "Broad_ID", measure.vars = colnames(dep)[2:ncol(dep)], variable.name = "Hugo_Symbol", value.name = "Dep_Prob")

# Merge dependency probabilities
crispr_melt <- merge(crispr_melt, dep_melt, by = c("Broad_ID", "Hugo_Symbol"), all.x = TRUE)

# Merge cell line metadata
crispr_melt <- merge(crispr_melt, ccl_info, by = "Broad_ID", all.x = TRUE)
crispr_melt <- merge(crispr_melt, crispr_meta, by = c("CCLE_Name", "Broad_ID"), all.x = TRUE)

# Merge mutation annotations
crispr_muts <- merge(crispr_melt, maf_df, by = c("Hugo_Symbol", "CCLE_Name", "Broad_ID"), all.x = TRUE)
crispr_muts$Hugo_Symbol <- factor(crispr_muts$Hugo_Symbol)
crispr_muts <- crispr_muts %>% mutate(Mutation_Status_Deleterious = if_else(is.na(Mutation_Status_Deleterious), "Other", Mutation_Status_Deleterious), Mutation_Status_DeleteriousMissense = if_else(is.na(Mutation_Status_DeleteriousMissense), "Other", Mutation_Status_DeleteriousMissense), Mutation_Status_Nonsilent = if_else(is.na(Mutation_Status_Nonsilent), "Other", Mutation_Status_Nonsilent))

# Summarize number of mutant and Other cell lines
crispr_muts_summ <- crispr_muts %>% group_by(Hugo_Symbol) %>%
  summarize(N_Deleterious_Other = sum(Mutation_Status_Deleterious == "Other"),
            N_Deleterious_Mutant = sum(Mutation_Status_Deleterious == "Mutant"),
            N_DeleteriousMissense_Other = sum(Mutation_Status_DeleteriousMissense == "Other"),
            N_DeleteriousMissense_Mutant = sum(Mutation_Status_DeleteriousMissense == "Mutant"),
            N_Nonsilent_Other = sum(Mutation_Status_Nonsilent == "Other"),
            N_Nonsilent_Mutant = sum(Mutation_Status_Nonsilent == "Mutant"))

# Merge test results back into full dataset, which restores information lost in the summarization
crispr_data <- merge(crispr_muts_summ, crispr_muts, by = "Hugo_Symbol")

# Add Color columns
crispr_data$Color_Deleterious <- ifelse(crispr_data$Mutation_Status_Deleterious == "Other", "cyan3", "darkorchid")
crispr_data$Color_Deleterious <- factor(crispr_data$Color_Deleterious)
crispr_data$Color_DeleteriousMissense <- ifelse(crispr_data$Mutation_Status_DeleteriousMissense == "Other", "cyan3", "darkorchid")
crispr_data$Color_DeleteriousMissense <- factor(crispr_data$Color_DeleteriousMissense)
crispr_data$Color_Nonsilent <- ifelse(crispr_data$Mutation_Status_Nonsilent == "Other", "cyan3", "darkorchid")
crispr_data$Color_Nonsilent <- factor(crispr_data$Color_Nonsilent)

# Cell line lineages
crispr_data <- merge(crispr_data, ccl_converter, by = c("CCLE_Name", "Broad_ID"), all.x = TRUE)
levels(crispr_data$lineage_name) <- sort(levels(crispr_data$lineage_name), decreasing = TRUE)

# Copy number
crispr_data <- merge(crispr_data, cn_melt, by = c("Hugo_Symbol", "Broad_ID"), all.x = TRUE)

# Gene expression (RPKM)
ge_filt <- filter(ge_melt, Hugo_Symbol %in% unique(crispr_data$Hugo_Symbol))
crispr_data <- merge(crispr_data, ge_filt, by = c("Hugo_Symbol", "Broad_ID", "CCLE_Name"), all.x = TRUE)
crispr_data$RPKM_log2 <- log2(crispr_data$RPKM + 0.0001)

saveRDS(crispr_data, "./../crispr_lineages_giant_files/crispr_data_18Q3.rds", compress = "xz")

crispr_data <- readRDS("./../crispr_lineages_giant_files/crispr_data_18Q3.rds")
crispr_ccl <- data.frame("Broad_ID" = crispr_data$Broad_ID)
# write.table(crispr_data, file = "~/Desktop/crispr_data.tsv", quote = FALSE, sep = "\t")

4 Wilcoxon tests: Point mutations

---

Filter for point mutations:

crispr_data_ptmuts <- filter(crispr_data, Var_Length == 1 | is.na(Var_Length))
test_ptmuts <- filter(crispr_data_ptmuts, is.na(group_general_lineage_name))
test_ptmuts <- filter(crispr_data_ptmuts, Hugo_Symbol == "KRAS")

4.1 Grouped by gene

4.1.1 Deleterious vs. Other

crispr_signif_del <- compare_means(Score ~ Mutation_Status_Deleterious, group.by = c("Hugo_Symbol"), data = crispr_data_ptmuts, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_del <- adj_signif(crispr_signif_del)
crispr_signif_del <- crispr_signif_del[order(crispr_signif_del$p),]
saveRDS(crispr_signif_del, "./data_munging/rds/crispr_signif_ptmuts_deleterious_gene.rds")

# write.table(crispr_signif_del, file = "~/Desktop/crispr_signif_ptmuts_deleterious_gene.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_del <- readRDS("./data_munging/rds/crispr_signif_ptmuts_deleterious_gene.rds")

knitr::kable(filter(crispr_signif_del, p < 0.01)[, c("Hugo_Symbol", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing deleterious mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing deleterious mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	p	p.adj	p.format	p.signif	p.signif.adj
PTEN	0.0000000	0.0000000	1.5e-12	****	****
TP53	0.0000008	0.0050305	7.7e-07	****	**
ARID1A	0.0000061	0.0265330	6.1e-06	****
UTP20	0.0000785	0.2560978	7.8e-05	****	NA
VHL	0.0001077	0.2812367	0.00011	***	NA
ARID1B	0.0003780	0.7461832	0.00038	***	NA
ZC3H13	0.0009610	0.7461832	0.00096	***	NA
ABCD4	0.0012457	0.7461832	0.00125	**	NA
RB1	0.0016928	0.7461832	0.00169	**	NA
RNF208	0.0019385	0.7461832	0.00194	**	NA
DENND1A	0.0020308	0.7461832	0.00203	**	NA
AJAP1	0.0021075	0.7461832	0.00211	**	NA
HAX1	0.0022315	0.7461832	0.00223	**	NA
NIPBL	0.0022374	0.7461832	0.00224	**	NA
TIMD4	0.0022527	0.7461832	0.00225	**	NA
ULK1	0.0023004	0.7461832	0.00230	**	NA
PIGR	0.0028348	0.7461832	0.00283	**	NA
TP53BP2	0.0029604	0.7461832	0.00296	**	NA
KLHL17	0.0038240	0.7461832	0.00382	**	NA
TUBGCP5	0.0039141	0.7461832	0.00391	**	NA
FMN1	0.0039763	0.7461832	0.00398	**	NA
AKAP13	0.0040426	0.7461832	0.00404	**	NA
PIK3R1	0.0040474	0.7461832	0.00405	**	NA
UGT2A3	0.0041569	0.7461832	0.00416	**	NA
ATAD5	0.0045229	0.7461832	0.00452	**	NA
TCERG1	0.0045495	0.7461832	0.00455	**	NA
KRT19	0.0046981	0.7461832	0.00470	**	NA
PPIL4	0.0047926	0.7461832	0.00479	**	NA
CR1	0.0048029	0.7461832	0.00480	**	NA
KIAA1731	0.0048110	0.7461832	0.00481	**	NA
RINT1	0.0048906	0.7461832	0.00489	**	NA
SIN3A	0.0049114	0.7461832	0.00491	**	NA
DLD	0.0053771	0.7461832	0.00538	**	NA
NPSR1	0.0054137	0.7461832	0.00541	**	NA
PTPRR	0.0055220	0.7461832	0.00552	**	NA
CSTF3	0.0055891	0.7461832	0.00559	**	NA
GSTM5	0.0058384	0.7461832	0.00584	**	NA
OLFML2B	0.0058575	0.7461832	0.00586	**	NA
ARID5B	0.0059256	0.7461832	0.00593	**	NA
TDRD7	0.0061289	0.7461832	0.00613	**	NA
NOC4L	0.0061581	0.7461832	0.00616	**	NA
KIAA1107	0.0061991	0.7461832	0.00620	**	NA
SLC28A2	0.0062191	0.7461832	0.00622	**	NA
PLXNA1	0.0062851	0.7461832	0.00629	**	NA
PLOD3	0.0062880	0.7461832	0.00629	**	NA
ZNF439	0.0063457	0.7461832	0.00635	**	NA
DMKN	0.0063484	0.7461832	0.00635	**	NA
EDNRB	0.0063517	0.7461832	0.00635	**	NA
UTP3	0.0065359	0.7461832	0.00654	**	NA
MSH6	0.0066097	0.7461832	0.00661	**	NA
ELTD1	0.0066592	0.7461832	0.00666	**	NA
ST7	0.0068047	0.7461832	0.00680	**	NA
IQCH	0.0068191	0.7461832	0.00682	**	NA
LILRB2	0.0071039	0.7461832	0.00710	**	NA
BRD4	0.0072117	0.7461832	0.00721	**	NA
UTS2B	0.0072533	0.7461832	0.00725	**	NA
KLHL1	0.0073975	0.7461832	0.00740	**	NA
RAD50	0.0075005	0.7461832	0.00750	**	NA
AMER2	0.0076915	0.7461832	0.00769	**	NA
DMWD	0.0077231	0.7461832	0.00772	**	NA
ATG2A	0.0077283	0.7461832	0.00773	**	NA
NPAT	0.0080167	0.7461832	0.00802	**	NA
SMARCB1	0.0081997	0.7461832	0.00820	**	NA
PAQR3	0.0082276	0.7461832	0.00823	**	NA
SF3B2	0.0084940	0.7461832	0.00849	**	NA
NGRN	0.0085338	0.7461832	0.00853	**	NA
SKOR1	0.0085338	0.7461832	0.00853	**	NA
PHLPP1	0.0085991	0.7461832	0.00860	**	NA
ZBTB25	0.0086381	0.7461832	0.00864	**	NA
ZNF124	0.0089578	0.7461832	0.00896	**	NA
TOP1MT	0.0089680	0.7461832	0.00897	**	NA
THEMIS	0.0092069	0.7461832	0.00921	**	NA
ESYT2	0.0092528	0.7461832	0.00925	**	NA
SRPR	0.0092882	0.7461832	0.00929	**	NA
PAX5	0.0093106	0.7461832	0.00931	**	NA
TTC22	0.0094474	0.7461832	0.00945	**	NA
BUB1	0.0095144	0.7461832	0.00951	**	NA
RIMBP3	0.0096462	0.7461832	0.00965	**	NA

wilcox_gene_plot <- ggplot(data = crispr_signif_del) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_gene_plot

4.1.2 Non-silent mutant vs. Other

crispr_signif_nonsilent <- compare_means(Score ~ Mutation_Status_Nonsilent, group.by = c("Hugo_Symbol"), data = crispr_data_ptmuts, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_nonsilent <- adj_signif(crispr_signif_nonsilent)
crispr_signif_nonsilent <- crispr_signif_nonsilent[order(crispr_signif_nonsilent$p),]
saveRDS(crispr_signif_nonsilent, "./data_munging/rds/crispr_signif_ptmuts_nonsilent_gene.rds")

# write.table(crispr_signif_nonsilent, file = "~/Desktop/crispr_signif_ptmuts_nonsilent_gene.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_nonsilent <- readRDS("./data_munging/rds/crispr_signif_ptmuts_nonsilent_gene.rds")

knitr::kable(filter(crispr_signif_nonsilent, p < 0.01)[, c("Hugo_Symbol", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing non-silent mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing non-silent mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	p	p.adj	p.format	p.signif	p.signif.adj
TP53	0.0000000	0.0000000	< 2e-16	****	****
KRAS	0.0000000	0.0000000	< 2e-16	****	****
NRAS	0.0000000	0.0000000	< 2e-16	****	****
BRAF	0.0000000	0.0000000	< 2e-16	****	****
PTEN	0.0000000	0.0000000	2.1e-15	****	****
PIK3CA	0.0000000	0.0000000	9.6e-14	****	****
CTNNB1	0.0000058	0.0143321	5.8e-06	****
TCERG1	0.0000135	0.0290351	1.4e-05	****
ARID1A	0.0000332	0.0633052	3.3e-05	****	NA
FCGBP	0.0000696	0.1195154	7.0e-05	****	NA
TPR	0.0000827	0.1213965	8.3e-05	****	NA
PIK3R1	0.0000848	0.1213965	8.5e-05	****	NA
TAOK2	0.0002289	0.3025013	0.00023	***	NA
SLC22A9	0.0002503	0.3032257	0.00025	***	NA
GSTM5	0.0002648	0.3032257	0.00026	***	NA
CPSF1	0.0003055	0.3280113	0.00031	***	NA
NIPBL	0.0003521	0.3306423	0.00035	***	NA
PIGW	0.0003638	0.3306423	0.00036	***	NA
C14orf39	0.0003657	0.3306423	0.00037	***	NA
TLX2	0.0004787	0.4111424	0.00048	***	NA
ARFGAP1	0.0005157	0.4156420	0.00052	***	NA
ZNF808	0.0005323	0.4156420	0.00053	***	NA
CD320	0.0005816	0.4343665	0.00058	***	NA
MAT2B	0.0007184	0.5086287	0.00072	***	NA
ZNF177	0.0007543	0.5086287	0.00075	***	NA
SYNPO2L	0.0007699	0.5086287	0.00077	***	NA
HRAS	0.0008408	0.5244580	0.00084	***	NA
UTP3	0.0008549	0.5244580	0.00085	***	NA
RNF208	0.0008907	0.5275698	0.00089	***	NA
KCNIP4	0.0009472	0.5423384	0.00095	***	NA
GOLGA3	0.0010340	0.5457674	0.00103	**	NA
DSEL	0.0010395	0.5457674	0.00104	**	NA
PROM1	0.0010485	0.5457674	0.00105	**	NA
PMPCA	0.0010990	0.5552227	0.00110	**	NA
OR52E8	0.0012095	0.5724468	0.00121	**	NA
OR13C4	0.0012702	0.5724468	0.00127	**	NA
TELO2	0.0012922	0.5724468	0.00129	**	NA
TAS1R2	0.0013163	0.5724468	0.00132	**	NA
ZNF439	0.0013227	0.5724468	0.00132	**	NA
MDN1	0.0013858	0.5724468	0.00139	**	NA
MTMR2	0.0014414	0.5724468	0.00144	**	NA
E2F1	0.0014486	0.5724468	0.00145	**	NA
LPO	0.0014636	0.5724468	0.00146	**	NA
ING2	0.0014811	0.5724468	0.00148	**	NA
PLA2G4F	0.0014997	0.5724468	0.00150	**	NA
MEF2C	0.0015423	0.5738410	0.00154	**	NA
UTP20	0.0015804	0.5738410	0.00158	**	NA
IQCH	0.0016077	0.5738410	0.00161	**	NA
PCDHB15	0.0016370	0.5738410	0.00164	**	NA
ACSM2B	0.0017107	0.5804214	0.00171	**	NA
OR8D1	0.0017233	0.5804214	0.00172	**	NA
RFC1	0.0018888	0.6183553	0.00189	**	NA
KIAA1211L	0.0019402	0.6183553	0.00194	**	NA
SENP8	0.0019559	0.6183553	0.00196	**	NA
RUVBL1	0.0019950	0.6183553	0.00200	**	NA
CLEC4C	0.0020667	0.6183553	0.00207	**	NA
PCDHA8	0.0020705	0.6183553	0.00207	**	NA
PI4K2A	0.0020961	0.6183553	0.00210	**	NA
KPNA6	0.0021334	0.6183553	0.00213	**	NA
POU2F1	0.0022102	0.6183553	0.00221	**	NA
BTBD11	0.0022318	0.6183553	0.00223	**	NA
FBXW7	0.0023109	0.6183553	0.00231	**	NA
ANKRD31	0.0023475	0.6183553	0.00235	**	NA
OR51T1	0.0023614	0.6183553	0.00236	**	NA
METTL17	0.0023923	0.6183553	0.00239	**	NA
CIITA	0.0024057	0.6183553	0.00241	**	NA
ADAM15	0.0024806	0.6183553	0.00248	**	NA
TUBB2A	0.0025373	0.6183553	0.00254	**	NA
RAB43	0.0025433	0.6183553	0.00254	**	NA
TAAR1	0.0025653	0.6183553	0.00257	**	NA
EZH2	0.0025733	0.6183553	0.00257	**	NA
ZDHHC24	0.0025919	0.6183553	0.00259	**	NA
SURF6	0.0027361	0.6245468	0.00274	**	NA
KIF11	0.0027512	0.6245468	0.00275	**	NA
VHL	0.0027587	0.6245468	0.00276	**	NA
GRM7	0.0027641	0.6245468	0.00276	**	NA
AVEN	0.0027997	0.6245468	0.00280	**	NA
OLFML2B	0.0029959	0.6248726	0.00300	**	NA
SAMM50	0.0030102	0.6248726	0.00301	**	NA
ACTA1	0.0030465	0.6248726	0.00305	**	NA
FRMD4B	0.0030803	0.6248726	0.00308	**	NA
SLC26A2	0.0030940	0.6248726	0.00309	**	NA
MYH13	0.0032183	0.6248726	0.00322	**	NA
LTC4S	0.0032514	0.6248726	0.00325	**	NA
MAP2K3	0.0032831	0.6248726	0.00328	**	NA
DIS3L2	0.0032847	0.6248726	0.00328	**	NA
PTPRE	0.0032929	0.6248726	0.00329	**	NA
CNOT1	0.0032940	0.6248726	0.00329	**	NA
ANKRD32	0.0034117	0.6248726	0.00341	**	NA
SCG2	0.0034839	0.6248726	0.00348	**	NA
TRIM8	0.0034895	0.6248726	0.00349	**	NA
CAMK2B	0.0035496	0.6248726	0.00355	**	NA
ETAA1	0.0035617	0.6248726	0.00356	**	NA
ST6GALNAC1	0.0035708	0.6248726	0.00357	**	NA
LILRB2	0.0036287	0.6248726	0.00363	**	NA
SLC38A7	0.0036411	0.6248726	0.00364	**	NA
SOX9	0.0036519	0.6248726	0.00365	**	NA
MMRN2	0.0036540	0.6248726	0.00365	**	NA
MAML2	0.0037079	0.6248726	0.00371	**	NA
POLG	0.0037209	0.6248726	0.00372	**	NA
SGCD	0.0037645	0.6248726	0.00376	**	NA
KRT83	0.0038147	0.6248726	0.00381	**	NA
RB1	0.0038228	0.6248726	0.00382	**	NA
SPAG17	0.0038410	0.6248726	0.00384	**	NA
EEF2	0.0038473	0.6248726	0.00385	**	NA
SUSD5	0.0039261	0.6248726	0.00393	**	NA
ATR	0.0039338	0.6248726	0.00393	**	NA
ATXN2L	0.0041364	0.6248726	0.00414	**	NA
CD83	0.0041819	0.6248726	0.00418	**	NA
TOP1MT	0.0042412	0.6248726	0.00424	**	NA
EMILIN3	0.0042659	0.6248726	0.00427	**	NA
SPHK2	0.0043100	0.6248726	0.00431	**	NA
PSMB4	0.0043587	0.6248726	0.00436	**	NA
ACHE	0.0043818	0.6248726	0.00438	**	NA
ZNF135	0.0045686	0.6248726	0.00457	**	NA
TPP1	0.0046303	0.6248726	0.00463	**	NA
NFE2L1	0.0046446	0.6248726	0.00464	**	NA
KHSRP	0.0046808	0.6248726	0.00468	**	NA
PPP1R1C	0.0047398	0.6248726	0.00474	**	NA
CDC37	0.0047810	0.6248726	0.00478	**	NA
CD200R1	0.0048862	0.6248726	0.00489	**	NA
CWH43	0.0048913	0.6248726	0.00489	**	NA
FOXRED1	0.0049144	0.6248726	0.00491	**	NA
HCRTR1	0.0049160	0.6248726	0.00492	**	NA
ZC3H4	0.0050449	0.6248726	0.00504	**	NA
RBBP9	0.0050826	0.6248726	0.00508	**	NA
OGFOD3	0.0051338	0.6248726	0.00513	**	NA
TBC1D22A	0.0052429	0.6248726	0.00524	**	NA
APOBEC1	0.0052779	0.6248726	0.00528	**	NA
OR56A3	0.0052916	0.6248726	0.00529	**	NA
SLC46A2	0.0053108	0.6248726	0.00531	**	NA
STK17B	0.0053176	0.6248726	0.00532	**	NA
PIGP	0.0053363	0.6248726	0.00534	**	NA
C6orf15	0.0053410	0.6248726	0.00534	**	NA
SMPD1	0.0053513	0.6248726	0.00535	**	NA
RNF43	0.0053669	0.6248726	0.00537	**	NA
FBXW12	0.0053691	0.6248726	0.00537	**	NA
RSPH6A	0.0053903	0.6248726	0.00539	**	NA
THADA	0.0055256	0.6248726	0.00553	**	NA
MYOC	0.0055382	0.6248726	0.00554	**	NA
SLC12A4	0.0056227	0.6248726	0.00562	**	NA
BTAF1	0.0056982	0.6248726	0.00570	**	NA
DNAJC5B	0.0057016	0.6248726	0.00570	**	NA
TAS2R60	0.0057034	0.6248726	0.00570	**	NA
IBA57	0.0057420	0.6248726	0.00574	**	NA
HSD3B7	0.0057475	0.6248726	0.00575	**	NA
HDGFRP2	0.0057596	0.6248726	0.00576	**	NA
MRPS34	0.0057928	0.6248726	0.00579	**	NA
SSH2	0.0058405	0.6248726	0.00584	**	NA
MBD3L2	0.0058844	0.6248726	0.00588	**	NA
COPS2	0.0059315	0.6248726	0.00593	**	NA
WDR75	0.0059969	0.6248726	0.00600	**	NA
FRYL	0.0060235	0.6248726	0.00602	**	NA
MUS81	0.0061273	0.6248726	0.00613	**	NA
CD5L	0.0061772	0.6248726	0.00618	**	NA
DPP7	0.0061926	0.6248726	0.00619	**	NA
LMX1A	0.0062097	0.6248726	0.00621	**	NA
ANTXRL	0.0062215	0.6248726	0.00622	**	NA
MMS22L	0.0062232	0.6248726	0.00622	**	NA
SFXN3	0.0062354	0.6248726	0.00624	**	NA
USP32	0.0062588	0.6248726	0.00626	**	NA
FAM181B	0.0062849	0.6248726	0.00628	**	NA
SMARCB1	0.0062993	0.6248726	0.00630	**	NA
ACBD6	0.0063036	0.6248726	0.00630	**	NA
SUPT7L	0.0063204	0.6248726	0.00632	**	NA
CYP19A1	0.0063281	0.6248726	0.00633	**	NA
C12orf4	0.0063501	0.6248726	0.00635	**	NA
FBXL20	0.0064106	0.6248726	0.00641	**	NA
NXPH4	0.0064264	0.6248726	0.00643	**	NA
CCNB1	0.0065022	0.6248726	0.00650	**	NA
LRGUK	0.0065445	0.6248726	0.00654	**	NA
OR4N2	0.0065455	0.6248726	0.00655	**	NA
RGS12	0.0065563	0.6248726	0.00656	**	NA
CEP76	0.0066070	0.6248726	0.00661	**	NA
MIIP	0.0066145	0.6248726	0.00661	**	NA
FCN3	0.0066248	0.6248726	0.00662	**	NA
ZNF107	0.0066752	0.6248726	0.00668	**	NA
TACSTD2	0.0066861	0.6248726	0.00669	**	NA
GLG1	0.0066950	0.6248726	0.00670	**	NA
TSPAN13	0.0067540	0.6248726	0.00675	**	NA
VPS13D	0.0067657	0.6248726	0.00677	**	NA
LPCAT4	0.0067758	0.6248726	0.00678	**	NA
ATXN2	0.0068586	0.6248726	0.00686	**	NA
DENND4C	0.0068602	0.6248726	0.00686	**	NA
ARID1B	0.0068718	0.6248726	0.00687	**	NA
KDM5B	0.0068837	0.6248726	0.00688	**	NA
IFFO2	0.0068857	0.6248726	0.00689	**	NA
COG3	0.0069083	0.6248726	0.00691	**	NA
DHX35	0.0069214	0.6248726	0.00692	**	NA
PPM1A	0.0069353	0.6248726	0.00694	**	NA
MSGN1	0.0069483	0.6248726	0.00695	**	NA
POC1A	0.0071368	0.6341224	0.00714	**	NA
CLDN5	0.0071709	0.6341224	0.00717	**	NA
PRKCZ	0.0072554	0.6341224	0.00726	**	NA
ACTL8	0.0072969	0.6341224	0.00730	**	NA
MGA	0.0073204	0.6341224	0.00732	**	NA
GTF3C1	0.0073309	0.6341224	0.00733	**	NA
SMCR8	0.0073359	0.6341224	0.00734	**	NA
HSPB2	0.0073660	0.6341224	0.00737	**	NA
EML1	0.0073834	0.6341224	0.00738	**	NA
INTS12	0.0075473	0.6405098	0.00755	**	NA
NAA15	0.0075638	0.6405098	0.00756	**	NA
SPTBN4	0.0075987	0.6405098	0.00760	**	NA
ARSB	0.0076069	0.6405098	0.00761	**	NA
VPS37B	0.0076704	0.6427055	0.00767	**	NA
CREBBP	0.0077132	0.6431501	0.00771	**	NA
NCR3LG1	0.0078580	0.6514880	0.00786	**	NA
ZNF493	0.0078890	0.6514880	0.00789	**	NA
AP5B1	0.0079487	0.6523618	0.00795	**	NA
ACYP2	0.0079841	0.6523618	0.00798	**	NA
C20orf26	0.0080463	0.6523618	0.00805	**	NA
PLOD1	0.0080515	0.6523618	0.00805	**	NA
OR4S2	0.0081035	0.6534954	0.00810	**	NA
SPO11	0.0081886	0.6568749	0.00819	**	NA
MCTP1	0.0082300	0.6568749	0.00823	**	NA
ELK3	0.0083459	0.6568749	0.00835	**	NA
H2AFY2	0.0083475	0.6568749	0.00835	**	NA
MRPL13	0.0083762	0.6568749	0.00838	**	NA
PAQR3	0.0084147	0.6568749	0.00841	**	NA
GHITM	0.0084474	0.6568749	0.00845	**	NA
ADO	0.0085378	0.6568749	0.00854	**	NA
MFAP4	0.0085654	0.6568749	0.00857	**	NA
CD163	0.0085663	0.6568749	0.00857	**	NA
ARMC7	0.0085988	0.6568749	0.00860	**	NA
COL8A1	0.0086043	0.6568749	0.00860	**	NA
NBPF15	0.0086920	0.6606339	0.00869	**	NA
OR13C3	0.0088398	0.6659977	0.00884	**	NA
COL7A1	0.0088402	0.6659977	0.00884	**	NA
C1orf141	0.0089498	0.6698168	0.00895	**	NA
ARHGEF17	0.0089894	0.6698168	0.00899	**	NA
COL9A2	0.0090078	0.6698168	0.00901	**	NA
DTHD1	0.0090748	0.6699801	0.00907	**	NA
LRP12	0.0090984	0.6699801	0.00910	**	NA
CCNL1	0.0091597	0.6699801	0.00916	**	NA
TMEM258	0.0091769	0.6699801	0.00918	**	NA
DNAJC8	0.0093058	0.6699801	0.00931	**	NA
KRTAP4-4	0.0093494	0.6699801	0.00935	**	NA
LCTL	0.0093837	0.6699801	0.00938	**	NA
ELMSAN1	0.0093954	0.6699801	0.00940	**	NA
SGK2	0.0093988	0.6699801	0.00940	**	NA
SLC25A4	0.0094344	0.6699801	0.00943	**	NA
F11R	0.0094708	0.6699801	0.00947	**	NA
LY6G6F	0.0095144	0.6699801	0.00951	**	NA
ZNF330	0.0095171	0.6699801	0.00952	**	NA
NECAB1	0.0095689	0.6708810	0.00957	**	NA
GMCL1	0.0096195	0.6710890	0.00962	**	NA
C16orf58	0.0096729	0.6710890	0.00967	**	NA
ZBTB44	0.0096904	0.6710890	0.00969	**	NA
INHBA	0.0097282	0.6710890	0.00973	**	NA
RNF31	0.0098119	0.6727895	0.00981	**	NA
CACNA1I	0.0098312	0.6727895	0.00983	**	NA
COPS3	0.0098996	0.6747558	0.00990	**	NA
NOL6	0.0099717	0.6747558	0.00997	**	NA
WDR77	0.0099778	0.6747558	0.00998	**	NA

wilcox_gene_nonsilent_plot <- ggplot(data = crispr_signif_nonsilent) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_gene_nonsilent_plot

4.1.3 Deleterious and missense mutant vs. Other

crispr_signif_delmis <- compare_means(Score ~ Mutation_Status_DeleteriousMissense, group.by = c("Hugo_Symbol"), data = crispr_data_ptmuts, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_delmis <- adj_signif(crispr_signif_delmis)
crispr_signif_delmis <- crispr_signif_delmis[order(crispr_signif_delmis$p),]
saveRDS(crispr_signif_delmis, "./data_munging/rds/crispr_signif_ptmuts_deleteriousmissense_gene.rds")

# write.table(crispr_signif_delmis, file = "~/Desktop/crispr_signif_ptmuts_deleteriousmissense_gene.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_delmis <- readRDS("./data_munging/rds/crispr_signif_ptmuts_deleteriousmissense_gene.rds")

knitr::kable(filter(crispr_signif_delmis, p < 0.01)[, c("Hugo_Symbol", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing deleterious and missense mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing deleterious and missense mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	p	p.adj	p.format	p.signif	p.signif.adj
KRAS	0.0000000	0.0000000	< 2e-16	****	****
TP53	0.0000000	0.0000000	< 2e-16	****	****
NRAS	0.0000000	0.0000000	< 2e-16	****	****
BRAF	0.0000000	0.0000000	< 2e-16	****	****
PTEN	0.0000000	0.0000000	2.1e-15	****	****
PIK3CA	0.0000000	0.0000000	9.6e-14	****	****
CTNNB1	0.0000058	0.0143296	5.8e-06	****
TCERG1	0.0000135	0.0290301	1.4e-05	****
ARID1A	0.0000332	0.0632941	3.3e-05	****	NA
FCGBP	0.0000696	0.1194946	7.0e-05	****	NA
TPR	0.0000827	0.1291821	8.3e-05	****	NA
SLC22A9	0.0002503	0.3498147	0.00025	***	NA
GSTM5	0.0002648	0.3498147	0.00026	***	NA
CPSF1	0.0003055	0.3748046	0.00031	***	NA
PIGW	0.0003638	0.3925692	0.00036	***	NA
C14orf39	0.0003657	0.3925692	0.00037	***	NA
TLX2	0.0004787	0.4540312	0.00048	***	NA
NIPBL	0.0005034	0.4540312	0.00050	***	NA
ARFGAP1	0.0005157	0.4540312	0.00052	***	NA
ZNF808	0.0005323	0.4540312	0.00053	***	NA
TAOK2	0.0005756	0.4540312	0.00058	***	NA
CD320	0.0005816	0.4540312	0.00058	***	NA
MAT2B	0.0007184	0.5125383	0.00072	***	NA
ZNF177	0.0007543	0.5125383	0.00075	***	NA
SYNPO2L	0.0007699	0.5125383	0.00077	***	NA
HRAS	0.0008408	0.5125383	0.00084	***	NA
UTP3	0.0008549	0.5125383	0.00085	***	NA
PIK3R1	0.0008568	0.5125383	0.00086	***	NA
RNF208	0.0008907	0.5125383	0.00089	***	NA
FBXW7	0.0008953	0.5125383	0.00090	***	NA
KCNIP4	0.0009472	0.5247519	0.00095	***	NA
GOLGA3	0.0010340	0.5296229	0.00103	**	NA
DSEL	0.0010395	0.5296229	0.00104	**	NA
PROM1	0.0010485	0.5296229	0.00105	**	NA
PMPCA	0.0010990	0.5392650	0.00110	**	NA
OR52E8	0.0012095	0.5479916	0.00121	**	NA
OR13C4	0.0012702	0.5479916	0.00127	**	NA
TELO2	0.0012922	0.5479916	0.00129	**	NA
TAS1R2	0.0013163	0.5479916	0.00132	**	NA
ZNF439	0.0013227	0.5479916	0.00132	**	NA
MDN1	0.0013858	0.5479916	0.00139	**	NA
MTMR2	0.0014414	0.5479916	0.00144	**	NA
E2F1	0.0014486	0.5479916	0.00145	**	NA
LPO	0.0014636	0.5479916	0.00146	**	NA
ING2	0.0014811	0.5479916	0.00148	**	NA
VHL	0.0014920	0.5479916	0.00149	**	NA
PLA2G4F	0.0014997	0.5479916	0.00150	**	NA
MEF2C	0.0015423	0.5512411	0.00154	**	NA
UTP20	0.0015804	0.5512411	0.00158	**	NA
IQCH	0.0016077	0.5512411	0.00161	**	NA
PCDHB15	0.0016370	0.5512411	0.00164	**	NA
ACSM2B	0.0017107	0.5584212	0.00171	**	NA
OR8D1	0.0017233	0.5584212	0.00172	**	NA
RFC1	0.0018888	0.5989004	0.00189	**	NA
KIAA1211L	0.0019402	0.5989004	0.00194	**	NA
SENP8	0.0019559	0.5989004	0.00196	**	NA
RUVBL1	0.0019950	0.5989004	0.00200	**	NA
CLEC4C	0.0020667	0.5989004	0.00207	**	NA
PCDHA8	0.0020705	0.5989004	0.00207	**	NA
PI4K2A	0.0020961	0.5989004	0.00210	**	NA
KPNA6	0.0021334	0.5989004	0.00213	**	NA
POU2F1	0.0022102	0.5989004	0.00221	**	NA
EZH2	0.0022226	0.5989004	0.00222	**	NA
BTBD11	0.0022318	0.5989004	0.00223	**	NA
ANKRD31	0.0023475	0.6075732	0.00235	**	NA
OR51T1	0.0023614	0.6075732	0.00236	**	NA
METTL17	0.0023923	0.6075732	0.00239	**	NA
CIITA	0.0024057	0.6075732	0.00241	**	NA
ADAM15	0.0024806	0.6174244	0.00248	**	NA
TUBB2A	0.0025373	0.6182473	0.00254	**	NA
TAAR1	0.0025653	0.6182473	0.00257	**	NA
ZDHHC24	0.0025919	0.6182473	0.00259	**	NA
SURF6	0.0027361	0.6329390	0.00274	**	NA
KIF11	0.0027512	0.6329390	0.00275	**	NA
GRM7	0.0027641	0.6329390	0.00276	**	NA
OLFML2B	0.0029959	0.6347331	0.00300	**	NA
SAMM50	0.0030102	0.6347331	0.00301	**	NA
ACTA1	0.0030465	0.6347331	0.00305	**	NA
FRMD4B	0.0030803	0.6347331	0.00308	**	NA
SLC26A2	0.0030940	0.6347331	0.00309	**	NA
MYH13	0.0032183	0.6347331	0.00322	**	NA
LTC4S	0.0032514	0.6347331	0.00325	**	NA
MAP2K3	0.0032831	0.6347331	0.00328	**	NA
DIS3L2	0.0032847	0.6347331	0.00328	**	NA
PTPRE	0.0032929	0.6347331	0.00329	**	NA
CNOT1	0.0032940	0.6347331	0.00329	**	NA
ANKRD32	0.0034117	0.6347331	0.00341	**	NA
SCG2	0.0034839	0.6347331	0.00348	**	NA
TRIM8	0.0034895	0.6347331	0.00349	**	NA
CAMK2B	0.0035496	0.6347331	0.00355	**	NA
ETAA1	0.0035617	0.6347331	0.00356	**	NA
ST6GALNAC1	0.0035708	0.6347331	0.00357	**	NA
SLC38A7	0.0036411	0.6347331	0.00364	**	NA
SOX9	0.0036519	0.6347331	0.00365	**	NA
MMRN2	0.0036540	0.6347331	0.00365	**	NA
SGCD	0.0037645	0.6347331	0.00376	**	NA
KRT83	0.0038147	0.6347331	0.00381	**	NA
RB1	0.0038228	0.6347331	0.00382	**	NA
SPAG17	0.0038410	0.6347331	0.00384	**	NA
EEF2	0.0038473	0.6347331	0.00385	**	NA
SUSD5	0.0039261	0.6347331	0.00393	**	NA
NOL7	0.0039331	0.6347331	0.00393	**	NA
ATR	0.0039338	0.6347331	0.00393	**	NA
AVEN	0.0041287	0.6347331	0.00413	**	NA
ATXN2L	0.0041364	0.6347331	0.00414	**	NA
CD83	0.0041819	0.6347331	0.00418	**	NA
TOP1MT	0.0042412	0.6347331	0.00424	**	NA
EMILIN3	0.0042659	0.6347331	0.00427	**	NA
SPHK2	0.0043100	0.6347331	0.00431	**	NA
PSMB4	0.0043587	0.6347331	0.00436	**	NA
ACHE	0.0043818	0.6347331	0.00438	**	NA
IQGAP3	0.0045407	0.6347331	0.00454	**	NA
ZNF135	0.0045686	0.6347331	0.00457	**	NA
TPP1	0.0046303	0.6347331	0.00463	**	NA
NFE2L1	0.0046446	0.6347331	0.00464	**	NA
KHSRP	0.0046808	0.6347331	0.00468	**	NA
PPP1R1C	0.0047398	0.6347331	0.00474	**	NA
CDC37	0.0047810	0.6347331	0.00478	**	NA
CD200R1	0.0048862	0.6347331	0.00489	**	NA
CWH43	0.0048913	0.6347331	0.00489	**	NA
FOXRED1	0.0049144	0.6347331	0.00491	**	NA
HCRTR1	0.0049160	0.6347331	0.00492	**	NA
ZC3H4	0.0050449	0.6347331	0.00504	**	NA
RBBP9	0.0050826	0.6347331	0.00508	**	NA
OGFOD3	0.0051338	0.6347331	0.00513	**	NA
TBC1D22A	0.0052429	0.6347331	0.00524	**	NA
APOBEC1	0.0052779	0.6347331	0.00528	**	NA
OR56A3	0.0052916	0.6347331	0.00529	**	NA
SLC46A2	0.0053108	0.6347331	0.00531	**	NA
PIGP	0.0053363	0.6347331	0.00534	**	NA
C6orf15	0.0053410	0.6347331	0.00534	**	NA
SMPD1	0.0053513	0.6347331	0.00535	**	NA
RNF43	0.0053669	0.6347331	0.00537	**	NA
FBXW12	0.0053691	0.6347331	0.00537	**	NA
RSPH6A	0.0053903	0.6347331	0.00539	**	NA
THADA	0.0055256	0.6347331	0.00553	**	NA
MYOC	0.0055382	0.6347331	0.00554	**	NA
SLC12A4	0.0056227	0.6347331	0.00562	**	NA
BTAF1	0.0056982	0.6347331	0.00570	**	NA
DNAJC5B	0.0057016	0.6347331	0.00570	**	NA
TAS2R60	0.0057034	0.6347331	0.00570	**	NA
IBA57	0.0057420	0.6347331	0.00574	**	NA
HSD3B7	0.0057475	0.6347331	0.00575	**	NA
HDGFRP2	0.0057596	0.6347331	0.00576	**	NA
MRPS34	0.0057928	0.6347331	0.00579	**	NA
SSH2	0.0058405	0.6347331	0.00584	**	NA
MBD3L2	0.0058844	0.6347331	0.00588	**	NA
COPS2	0.0059315	0.6347331	0.00593	**	NA
WDR75	0.0059969	0.6347331	0.00600	**	NA
FRYL	0.0060235	0.6347331	0.00602	**	NA
ATXN2	0.0060319	0.6347331	0.00603	**	NA
NBPF15	0.0060598	0.6347331	0.00606	**	NA
MUS81	0.0061273	0.6347331	0.00613	**	NA
CD5L	0.0061772	0.6347331	0.00618	**	NA
DPP7	0.0061926	0.6347331	0.00619	**	NA
LMX1A	0.0062097	0.6347331	0.00621	**	NA
ANTXRL	0.0062215	0.6347331	0.00622	**	NA
MMS22L	0.0062232	0.6347331	0.00622	**	NA
SFXN3	0.0062354	0.6347331	0.00624	**	NA
USP32	0.0062588	0.6347331	0.00626	**	NA
RAB43	0.0062666	0.6347331	0.00627	**	NA
FAM181B	0.0062849	0.6347331	0.00628	**	NA
SMARCB1	0.0062993	0.6347331	0.00630	**	NA
ACBD6	0.0063036	0.6347331	0.00630	**	NA
SUPT7L	0.0063204	0.6347331	0.00632	**	NA
CYP19A1	0.0063281	0.6347331	0.00633	**	NA
C12orf4	0.0063501	0.6347331	0.00635	**	NA
FBXL20	0.0064106	0.6347331	0.00641	**	NA
NXPH4	0.0064264	0.6347331	0.00643	**	NA
CCNB1	0.0065022	0.6347331	0.00650	**	NA
OR4N2	0.0065455	0.6347331	0.00655	**	NA
RGS12	0.0065563	0.6347331	0.00656	**	NA
CEP76	0.0066070	0.6347331	0.00661	**	NA
MIIP	0.0066145	0.6347331	0.00661	**	NA
FCN3	0.0066248	0.6347331	0.00662	**	NA
ZNF107	0.0066752	0.6347331	0.00668	**	NA
TACSTD2	0.0066861	0.6347331	0.00669	**	NA
GLG1	0.0066950	0.6347331	0.00670	**	NA
TSPAN13	0.0067540	0.6347331	0.00675	**	NA
VPS13D	0.0067657	0.6347331	0.00677	**	NA
LPCAT4	0.0067758	0.6347331	0.00678	**	NA
DENND4C	0.0068602	0.6347331	0.00686	**	NA
ARID1B	0.0068718	0.6347331	0.00687	**	NA
KDM5B	0.0068837	0.6347331	0.00688	**	NA
IFFO2	0.0068857	0.6347331	0.00689	**	NA
COG3	0.0069083	0.6347331	0.00691	**	NA
DHX35	0.0069214	0.6347331	0.00692	**	NA
MSGN1	0.0069483	0.6347331	0.00695	**	NA
CLDN5	0.0071709	0.6515991	0.00717	**	NA
PRKCZ	0.0072554	0.6527818	0.00726	**	NA
ACTL8	0.0072969	0.6527818	0.00730	**	NA
MGA	0.0073204	0.6527818	0.00732	**	NA
SMCR8	0.0073359	0.6527818	0.00734	**	NA
EML1	0.0073834	0.6536203	0.00738	**	NA
F11R	0.0075268	0.6564883	0.00753	**	NA
INTS12	0.0075473	0.6564883	0.00755	**	NA
NAA15	0.0075638	0.6564883	0.00756	**	NA
SPTBN4	0.0075987	0.6564883	0.00760	**	NA
ARSB	0.0076069	0.6564883	0.00761	**	NA
VPS37B	0.0076704	0.6586581	0.00767	**	NA
CREBBP	0.0077132	0.6590337	0.00771	**	NA
NCR3LG1	0.0078580	0.6680868	0.00786	**	NA
AP5B1	0.0079487	0.6712453	0.00795	**	NA
ACYP2	0.0079841	0.6712453	0.00798	**	NA
C20orf26	0.0080463	0.6712453	0.00805	**	NA
PLOD1	0.0080515	0.6712453	0.00805	**	NA
OR4S2	0.0081035	0.6723199	0.00810	**	NA
SPO11	0.0081886	0.6747536	0.00819	**	NA
MCTP1	0.0082300	0.6747536	0.00823	**	NA
ELK3	0.0083459	0.6747536	0.00835	**	NA
H2AFY2	0.0083475	0.6747536	0.00835	**	NA
MRPL13	0.0083762	0.6747536	0.00838	**	NA
PAQR3	0.0084147	0.6747536	0.00841	**	NA
GHITM	0.0084474	0.6747536	0.00845	**	NA
ADO	0.0085378	0.6747536	0.00854	**	NA
MFAP4	0.0085654	0.6747536	0.00857	**	NA
CD163	0.0085663	0.6747536	0.00857	**	NA
ARMC7	0.0085988	0.6747536	0.00860	**	NA
COL8A1	0.0086043	0.6747536	0.00860	**	NA
LILRB2	0.0088241	0.6822660	0.00882	**	NA
OR13C3	0.0088398	0.6822660	0.00884	**	NA
COL7A1	0.0088402	0.6822660	0.00884	**	NA
C1orf141	0.0089498	0.6822660	0.00895	**	NA
ARHGEF17	0.0089894	0.6822660	0.00899	**	NA
COL9A2	0.0090078	0.6822660	0.00901	**	NA
DTHD1	0.0090748	0.6822660	0.00907	**	NA
H3F3A	0.0090755	0.6822660	0.00908	**	NA
LRP12	0.0090984	0.6822660	0.00910	**	NA
CCNL1	0.0091597	0.6822660	0.00916	**	NA
MAML2	0.0091672	0.6822660	0.00917	**	NA
TMEM258	0.0091769	0.6822660	0.00918	**	NA
DNAJC8	0.0093058	0.6835655	0.00931	**	NA
KRTAP4-4	0.0093494	0.6835655	0.00935	**	NA
LCTL	0.0093837	0.6835655	0.00938	**	NA
SGK2	0.0093988	0.6835655	0.00940	**	NA
SLC25A4	0.0094344	0.6835655	0.00943	**	NA
LY6G6F	0.0095144	0.6835655	0.00951	**	NA
ZNF330	0.0095171	0.6835655	0.00952	**	NA
NECAB1	0.0095689	0.6835655	0.00957	**	NA
PPM1A	0.0095782	0.6835655	0.00958	**	NA
GMCL1	0.0096195	0.6835655	0.00962	**	NA
C16orf58	0.0096729	0.6835655	0.00967	**	NA
ZBTB44	0.0096904	0.6835655	0.00969	**	NA
INHBA	0.0097282	0.6835655	0.00973	**	NA
GTF3C1	0.0097721	0.6835655	0.00977	**	NA
RNF31	0.0098119	0.6835655	0.00981	**	NA
CACNA1I	0.0098312	0.6835655	0.00983	**	NA
COPS3	0.0098996	0.6854321	0.00990	**	NA
NOL6	0.0099717	0.6854321	0.00997	**	NA
WDR77	0.0099778	0.6854321	0.00998	**	NA

wilcox_gene_delmis_plot <- ggplot(data = crispr_signif_delmis) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_gene_delmis_plot

4.2 Grouped by gene and lineage

4.2.1 Deleterious vs. Other

crispr_signif_del_lineage <- compare_means(Score ~ Mutation_Status_Deleterious, group.by = c("Hugo_Symbol", "group_general_lineage_name"), data = crispr_data_ptmuts, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_del_lineage <- adj_signif(crispr_signif_del_lineage)
crispr_signif_del_lineage <- crispr_signif_del_lineage[order(crispr_signif_del_lineage$p),]
saveRDS(crispr_signif_del_lineage, "./data_munging/rds/crispr_signif_ptmuts_deleterious_lineage.rds")

# write.table(crispr_signif_del_lineage, file = "~/Desktop/crispr_signif_ptmuts_deleterious_lineage.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_del_lineage <- readRDS("./data_munging/rds/crispr_signif_ptmuts_deleterious_lineage.rds")

knitr::kable(filter(crispr_signif_del_lineage, p < 0.01)[, c("Hugo_Symbol", "group_general_lineage_name", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing deleterious mutant vs other cell lines by lineage, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing deleterious mutant vs other cell lines by lineage, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	group_general_lineage_name	p	p.adj	p.format	p.signif	p.signif.adj
PTEN	central nervous system cancer	0.0006658	0.8370371	0.00067	***	NA
TP53	lung cancer	0.0007958	0.8370371	0.00080	***	NA
DCAF8	lung cancer	0.0033009	0.8370371	0.00330	**	NA
PTEN	ovarian cancer	0.0043470	0.8370371	0.00435	**	NA
SETD2	kidney cancer	0.0056647	0.8370371	0.00566	**	NA
DVL2	uterine cancer	0.0067676	0.8370371	0.00677	**	NA
ARID1A	pancreatic cancer	0.0076726	0.8370371	0.00767	**	NA
MCPH1	lung cancer	0.0077467	0.8370371	0.00775	**	NA

wilcox_lineage_plot <- ggplot(data = crispr_signif_del_lineage) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_lineage_plot

4.2.2 Non-silent mutant vs. Other

crispr_signif_nonsilent_lineage <- compare_means(Score ~ Mutation_Status_Nonsilent, group.by = c("Hugo_Symbol", "group_general_lineage_name"), data = crispr_data_ptmuts, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_nonsilent_lineage <- adj_signif(crispr_signif_nonsilent_lineage)
crispr_signif_nonsilent_lineage <- crispr_signif_nonsilent_lineage[order(crispr_signif_nonsilent_lineage$p),]
saveRDS(crispr_signif_nonsilent_lineage, "./data_munging/rds/crispr_signif_ptmuts_nonsilent_lineage.rds")

# write.table(crispr_signif_nonsilent_lineage, file = "~/Desktop/crispr_signif_ptmuts_nonsilent_lineage.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_nonsilent_lineage <- readRDS("./data_munging/rds/crispr_signif_ptmuts_nonsilent_lineage.rds")

knitr::kable(filter(crispr_signif_nonsilent_lineage, p < 0.01)[, c("Hugo_Symbol", "group_general_lineage_name", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing non-silent mutant vs other cell lines by lineage, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing non-silent mutant vs other cell lines by lineage, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	group_general_lineage_name	p	p.adj	p.format	p.signif	p.signif.adj
KRAS	lung cancer	0.0000000	0.0003131	2.5e-09	****	***
TP53	lung cancer	0.0000092	0.5639398	9.2e-06	****	NA
TP53	central nervous system cancer	0.0000386	0.8671069	3.9e-05	****	NA
KRAS	ovarian cancer	0.0001488	0.8671069	0.00015	***	NA
TP53	ovarian cancer	0.0002344	0.8671069	0.00023	***	NA
NRAS	leukemia	0.0005316	0.8671069	0.00053	***	NA
PIK3CA	ovarian cancer	0.0008371	0.8671069	0.00084	***	NA
DZANK1	breast cancer	0.0009819	0.8671069	0.00098	***	NA
PIK3CA	breast cancer	0.0009842	0.8671069	0.00098	***	NA
KRAS	colorectal cancer	0.0010547	0.8671069	0.00105	**	NA
TP53	leukemia	0.0010605	0.8671069	0.00106	**	NA
UNC45B	lung cancer	0.0011215	0.8671069	0.00112	**	NA
GOLGA3	uterine cancer	0.0013666	0.8671069	0.00137	**	NA
NRAS	multiple myeloma	0.0013756	0.8671069	0.00138	**	NA
GTF3C1	lung cancer	0.0013893	0.8671069	0.00139	**	NA
TICRR	uterine cancer	0.0014839	0.8671069	0.00148	**	NA
ARID1A	pancreatic cancer	0.0014920	0.8671069	0.00149	**	NA
NRAS	skin cancer	0.0016637	0.8671069	0.00166	**	NA
HYOU1	colorectal cancer	0.0018107	0.8671069	0.00181	**	NA
USP34	breast cancer	0.0018820	0.8671069	0.00188	**	NA
MGA	uterine cancer	0.0019495	0.8671069	0.00195	**	NA
TNRC6A	lung cancer	0.0023744	0.8671069	0.00237	**	NA
SNX29	uterine cancer	0.0026104	0.8671069	0.00261	**	NA
KMT2B	breast cancer	0.0026433	0.8671069	0.00264	**	NA
TP53	kidney cancer	0.0027562	0.8671069	0.00276	**	NA
GSPT1	colorectal cancer	0.0028115	0.8671069	0.00281	**	NA
AP1G2	breast cancer	0.0029835	0.8671069	0.00298	**	NA
ZNF264	colorectal cancer	0.0029879	0.8671069	0.00299	**	NA
PTEN	ovarian cancer	0.0032141	0.8671069	0.00321	**	NA
KMT2B	ovarian cancer	0.0032684	0.8671069	0.00327	**	NA
KIAA0586	colorectal cancer	0.0032838	0.8671069	0.00328	**	NA
ANK2	colorectal cancer	0.0033597	0.8671069	0.00336	**	NA
TGS1	uterine cancer	0.0035864	0.8671069	0.00359	**	NA
COL2A1	leukemia	0.0036054	0.8671069	0.00361	**	NA
HYDIN	colorectal cancer	0.0036704	0.8671069	0.00367	**	NA
TP53	colorectal cancer	0.0036994	0.8671069	0.00370	**	NA
TP53	skin cancer	0.0037227	0.8671069	0.00372	**	NA
VHL	kidney cancer	0.0037539	0.8671069	0.00375	**	NA
PAPPA	uterine cancer	0.0037971	0.8671069	0.00380	**	NA
ZNF292	lung cancer	0.0038193	0.8671069	0.00382	**	NA
PTEN	central nervous system cancer	0.0038648	0.8671069	0.00386	**	NA
NEBL	uterine cancer	0.0039522	0.8671069	0.00395	**	NA
KRAS	stomach cancer	0.0040001	0.8671069	0.00400	**	NA
MTMR3	lung cancer	0.0041192	0.8671069	0.00412	**	NA
TSKS	uterine cancer	0.0042550	0.8671069	0.00425	**	NA
ARHGAP12	colorectal cancer	0.0042860	0.8671069	0.00429	**	NA
PAM	uterine cancer	0.0043488	0.8671069	0.00435	**	NA
PDE10A	uterine cancer	0.0043488	0.8671069	0.00435	**	NA
MAML2	uterine cancer	0.0044510	0.8671069	0.00445	**	NA
NCOR2	colorectal cancer	0.0046575	0.8671069	0.00466	**	NA
VAV3	lung cancer	0.0047769	0.8671069	0.00478	**	NA
SYNE1	lung cancer	0.0047800	0.8671069	0.00478	**	NA
NUP88	uterine cancer	0.0048888	0.8671069	0.00489	**	NA
LRRIQ1	central nervous system cancer	0.0049271	0.8671069	0.00493	**	NA
SVOPL	lung cancer	0.0049276	0.8671069	0.00493	**	NA
PTEN	uterine cancer	0.0049419	0.8671069	0.00494	**	NA
BRAF	skin cancer	0.0049885	0.8671069	0.00499	**	NA
AXIN1	ovarian cancer	0.0050354	0.8671069	0.00504	**	NA
TNK2	uterine cancer	0.0050864	0.8671069	0.00509	**	NA
DIP2C	kidney cancer	0.0052747	0.8671069	0.00527	**	NA
CTAGE15	lung cancer	0.0053375	0.8671069	0.00534	**	NA
LSP1	colorectal cancer	0.0053452	0.8671069	0.00535	**	NA
CORIN	colorectal cancer	0.0054756	0.8671069	0.00548	**	NA
SETD2	kidney cancer	0.0056647	0.8671069	0.00566	**	NA
FNDC7	colorectal cancer	0.0057059	0.8671069	0.00571	**	NA
SKOR1	uterine cancer	0.0057795	0.8671069	0.00578	**	NA
PARD3B	uterine cancer	0.0059302	0.8671069	0.00593	**	NA
HTR7	lung cancer	0.0059492	0.8671069	0.00595	**	NA
FNIP1	ovarian cancer	0.0060557	0.8671069	0.00606	**	NA
AP2A2	breast cancer	0.0061570	0.8671069	0.00616	**	NA
ASXL1	colorectal cancer	0.0061648	0.8671069	0.00616	**	NA
CCT8L2	colorectal cancer	0.0061648	0.8671069	0.00616	**	NA
MTMR14	colorectal cancer	0.0061648	0.8671069	0.00616	**	NA
TTC32	uterine cancer	0.0062881	0.8671069	0.00629	**	NA
PIK3R1	ovarian cancer	0.0062895	0.8671069	0.00629	**	NA
NR4A1	lung cancer	0.0064934	0.8671069	0.00649	**	NA
SLC22A17	lung cancer	0.0064934	0.8671069	0.00649	**	NA
FAM208B	colorectal cancer	0.0065065	0.8671069	0.00651	**	NA
ROCK1	colorectal cancer	0.0066106	0.8671069	0.00661	**	NA
ZNF521	colorectal cancer	0.0066975	0.8671069	0.00670	**	NA
RFWD3	lung cancer	0.0067488	0.8671069	0.00675	**	NA
TYRP1	lung cancer	0.0067488	0.8671069	0.00675	**	NA
ADRBK2	uterine cancer	0.0067676	0.8671069	0.00677	**	NA
DVL2	uterine cancer	0.0067676	0.8671069	0.00677	**	NA
EXOC8	uterine cancer	0.0067676	0.8671069	0.00677	**	NA
ITSN1	colorectal cancer	0.0069403	0.8671069	0.00694	**	NA
ZNF292	colorectal cancer	0.0069403	0.8671069	0.00694	**	NA
MIS18BP1	colorectal cancer	0.0070098	0.8671069	0.00701	**	NA
OR5M8	colorectal cancer	0.0070184	0.8671069	0.00702	**	NA
LILRB2	leukemia	0.0070255	0.8671069	0.00703	**	NA
PIK3CA	colorectal cancer	0.0070506	0.8671069	0.00705	**	NA
DDX11	lung cancer	0.0070952	0.8671069	0.00710	**	NA
KMT2C	multiple myeloma	0.0071541	0.8671069	0.00715	**	NA
MYH6	uterine cancer	0.0071786	0.8671069	0.00718	**	NA
ARID1B	ovarian cancer	0.0072055	0.8671069	0.00721	**	NA
SURF6	uterine cancer	0.0073058	0.8671069	0.00731	**	NA
C1orf86	leukemia	0.0073710	0.8671069	0.00737	**	NA
TEX10	ovarian cancer	0.0075601	0.8671069	0.00756	**	NA
ALPK3	ovarian cancer	0.0076300	0.8671069	0.00763	**	NA
MYOM3	lung cancer	0.0076435	0.8671069	0.00764	**	NA
PNPLA5	colorectal cancer	0.0077740	0.8671069	0.00777	**	NA
PTGFRN	lung cancer	0.0078691	0.8671069	0.00787	**	NA
PCDH10	uterine cancer	0.0078925	0.8671069	0.00789	**	NA
ANKRD23	colorectal cancer	0.0078965	0.8671069	0.00790	**	NA
HERC1	skin cancer	0.0079501	0.8671069	0.00795	**	NA
C12orf4	uterine cancer	0.0080215	0.8671069	0.00802	**	NA
EGFLAM	lung cancer	0.0081906	0.8671069	0.00819	**	NA
SPRED1	lung cancer	0.0084512	0.8671069	0.00845	**	NA
SBF2	lung cancer	0.0084541	0.8671069	0.00845	**	NA
EFCAB5	ovarian cancer	0.0084624	0.8671069	0.00846	**	NA
CSNK1D	uterine cancer	0.0085754	0.8671069	0.00858	**	NA
FAM110A	uterine cancer	0.0085754	0.8671069	0.00858	**	NA
MICAL1	uterine cancer	0.0085754	0.8671069	0.00858	**	NA
MORF4L1	uterine cancer	0.0085754	0.8671069	0.00858	**	NA
RIOK2	uterine cancer	0.0085754	0.8671069	0.00858	**	NA
GAA	colorectal cancer	0.0085960	0.8671069	0.00860	**	NA
KIAA1107	colorectal cancer	0.0085960	0.8671069	0.00860	**	NA
ZNF536	skin cancer	0.0086987	0.8671069	0.00870	**	NA
RPS6KA2	uterine cancer	0.0087779	0.8671069	0.00878	**	NA
SOGA1	lung cancer	0.0088239	0.8671069	0.00882	**	NA
TPR	lung cancer	0.0088831	0.8671069	0.00888	**	NA
TECRL	lung cancer	0.0089331	0.8671069	0.00893	**	NA
SVEP1	skin cancer	0.0090238	0.8671069	0.00902	**	NA
DPYSL5	uterine cancer	0.0091517	0.8671069	0.00915	**	NA
FAM189A1	uterine cancer	0.0091517	0.8671069	0.00915	**	NA
HSPB2	uterine cancer	0.0091517	0.8671069	0.00915	**	NA
IRX6	uterine cancer	0.0091517	0.8671069	0.00915	**	NA
XKR9	uterine cancer	0.0091517	0.8671069	0.00915	**	NA
KIAA0922	lung cancer	0.0091532	0.8671069	0.00915	**	NA
STK17B	lung cancer	0.0092125	0.8671069	0.00921	**	NA
TTF1	lung cancer	0.0092125	0.8671069	0.00921	**	NA
TBC1D10B	uterine cancer	0.0092568	0.8671069	0.00926	**	NA
DNAJC8	uterine cancer	0.0092717	0.8671069	0.00927	**	NA
PKDCC	uterine cancer	0.0092717	0.8671069	0.00927	**	NA
TCF3	uterine cancer	0.0092717	0.8671069	0.00927	**	NA
ZNF207	uterine cancer	0.0093098	0.8671069	0.00931	**	NA
RASIP1	colorectal cancer	0.0093199	0.8671069	0.00932	**	NA
AP5B1	uterine cancer	0.0093215	0.8671069	0.00932	**	NA
RAD50	leukemia	0.0094090	0.8671069	0.00941	**	NA
KRT17	breast cancer	0.0094667	0.8671069	0.00947	**	NA
SCFD1	colorectal cancer	0.0094882	0.8671069	0.00949	**	NA
DNAH5	colorectal cancer	0.0095928	0.8671069	0.00959	**	NA
INTS4	uterine cancer	0.0096407	0.8671069	0.00964	**	NA
TTF1	leukemia	0.0097690	0.8671069	0.00977	**	NA
LRP4	uterine cancer	0.0099566	0.8671069	0.00996	**	NA
ZNF469	uterine cancer	0.0099581	0.8671069	0.00996	**	NA
IPO4	uterine cancer	0.0099688	0.8671069	0.00997	**	NA

wilcox_lineage_nonsilent_plot <- ggplot(data = crispr_signif_nonsilent_lineage) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_lineage_nonsilent_plot

4.2.3 Deleterious and missense mutant vs. Other

crispr_signif_delmis_lineage <- compare_means(Score ~ Mutation_Status_DeleteriousMissense, group.by = c("Hugo_Symbol", "group_general_lineage_name"), data = crispr_data_ptmuts, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_delmis_lineage <- adj_signif(crispr_signif_delmis_lineage)
crispr_signif_delmis_lineage <- crispr_signif_delmis_lineage[order(crispr_signif_delmis_lineage$p),]
saveRDS(crispr_signif_delmis_lineage, "./data_munging/rds/crispr_signif_ptmuts_deleteriousmissense_lineage.rds")

# write.table(crispr_signif_delmis_lineage, file = "~/Desktop/crispr_signif_ptmuts_deleteriousmissense_lineage.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_delmis_lineage <- readRDS("./data_munging/rds/crispr_signif_ptmuts_deleteriousmissense_lineage.rds")

knitr::kable(filter(crispr_signif_delmis_lineage, p < 0.01)[, c("Hugo_Symbol", "group_general_lineage_name", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing deleterious and missense mutant vs other cell lines by lineage, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing deleterious and missense mutant vs other cell lines by lineage, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	group_general_lineage_name	p	p.adj	p.format	p.signif	p.signif.adj
KRAS	lung cancer	0.0000000	0.0003122	2.5e-09	****	***
TP53	lung cancer	0.0000092	0.5624195	9.2e-06	****	NA
KRAS	ovarian cancer	0.0001488	0.8669363	0.00015	***	NA
TP53	central nervous system cancer	0.0001651	0.8669363	0.00017	***	NA
TP53	ovarian cancer	0.0002344	0.8669363	0.00023	***	NA
NRAS	leukemia	0.0005316	0.8669363	0.00053	***	NA
PIK3CA	ovarian cancer	0.0008371	0.8669363	0.00084	***	NA
DZANK1	breast cancer	0.0009819	0.8669363	0.00098	***	NA
PIK3CA	breast cancer	0.0009842	0.8669363	0.00098	***	NA
KRAS	colorectal cancer	0.0010547	0.8669363	0.00105	**	NA
TP53	leukemia	0.0010605	0.8669363	0.00106	**	NA
UNC45B	lung cancer	0.0011215	0.8669363	0.00112	**	NA
GOLGA3	uterine cancer	0.0013666	0.8669363	0.00137	**	NA
NRAS	multiple myeloma	0.0013756	0.8669363	0.00138	**	NA
GTF3C1	lung cancer	0.0013893	0.8669363	0.00139	**	NA
TICRR	uterine cancer	0.0014839	0.8669363	0.00148	**	NA
ARID1A	pancreatic cancer	0.0014920	0.8669363	0.00149	**	NA
NRAS	skin cancer	0.0016637	0.8669363	0.00166	**	NA
HYOU1	colorectal cancer	0.0018107	0.8669363	0.00181	**	NA
USP34	breast cancer	0.0018820	0.8669363	0.00188	**	NA
MGA	uterine cancer	0.0019495	0.8669363	0.00195	**	NA
TNRC6A	lung cancer	0.0023744	0.8669363	0.00237	**	NA
SNX29	uterine cancer	0.0026104	0.8669363	0.00261	**	NA
KMT2B	breast cancer	0.0026433	0.8669363	0.00264	**	NA
TP53	kidney cancer	0.0027562	0.8669363	0.00276	**	NA
GSPT1	colorectal cancer	0.0028115	0.8669363	0.00281	**	NA
AP1G2	breast cancer	0.0029835	0.8669363	0.00298	**	NA
ZNF264	colorectal cancer	0.0029879	0.8669363	0.00299	**	NA
PTEN	ovarian cancer	0.0032141	0.8669363	0.00321	**	NA
KMT2B	ovarian cancer	0.0032684	0.8669363	0.00327	**	NA
KIAA0586	colorectal cancer	0.0032838	0.8669363	0.00328	**	NA
ANK2	colorectal cancer	0.0033597	0.8669363	0.00336	**	NA
TGS1	uterine cancer	0.0035864	0.8669363	0.00359	**	NA
COL2A1	leukemia	0.0036054	0.8669363	0.00361	**	NA
HYDIN	colorectal cancer	0.0036704	0.8669363	0.00367	**	NA
TP53	colorectal cancer	0.0036994	0.8669363	0.00370	**	NA
TP53	skin cancer	0.0037227	0.8669363	0.00372	**	NA
VHL	kidney cancer	0.0037539	0.8669363	0.00375	**	NA
PAPPA	uterine cancer	0.0037971	0.8669363	0.00380	**	NA
ZNF292	lung cancer	0.0038193	0.8669363	0.00382	**	NA
PTEN	central nervous system cancer	0.0038648	0.8669363	0.00386	**	NA
NEBL	uterine cancer	0.0039522	0.8669363	0.00395	**	NA
KRAS	stomach cancer	0.0040001	0.8669363	0.00400	**	NA
MTMR3	lung cancer	0.0041192	0.8669363	0.00412	**	NA
TSKS	uterine cancer	0.0042550	0.8669363	0.00425	**	NA
ARHGAP12	colorectal cancer	0.0042860	0.8669363	0.00429	**	NA
PAM	uterine cancer	0.0043488	0.8669363	0.00435	**	NA
PDE10A	uterine cancer	0.0043488	0.8669363	0.00435	**	NA
NCOR2	colorectal cancer	0.0046575	0.8669363	0.00466	**	NA
VAV3	lung cancer	0.0047769	0.8669363	0.00478	**	NA
SYNE1	lung cancer	0.0047800	0.8669363	0.00478	**	NA
NUP88	uterine cancer	0.0048888	0.8669363	0.00489	**	NA
LRRIQ1	central nervous system cancer	0.0049271	0.8669363	0.00493	**	NA
SVOPL	lung cancer	0.0049276	0.8669363	0.00493	**	NA
PTEN	uterine cancer	0.0049419	0.8669363	0.00494	**	NA
BRAF	skin cancer	0.0049885	0.8669363	0.00499	**	NA
AXIN1	ovarian cancer	0.0050354	0.8669363	0.00504	**	NA
TNK2	uterine cancer	0.0050864	0.8669363	0.00509	**	NA
DIP2C	kidney cancer	0.0052747	0.8669363	0.00527	**	NA
CTAGE15	lung cancer	0.0053375	0.8669363	0.00534	**	NA
LSP1	colorectal cancer	0.0053452	0.8669363	0.00535	**	NA
CORIN	colorectal cancer	0.0054756	0.8669363	0.00548	**	NA
SETD2	kidney cancer	0.0056647	0.8669363	0.00566	**	NA
FNDC7	colorectal cancer	0.0057059	0.8669363	0.00571	**	NA
SKOR1	uterine cancer	0.0057795	0.8669363	0.00578	**	NA
PARD3B	uterine cancer	0.0059302	0.8669363	0.00593	**	NA
HTR7	lung cancer	0.0059492	0.8669363	0.00595	**	NA
FNIP1	ovarian cancer	0.0060557	0.8669363	0.00606	**	NA
AP2A2	breast cancer	0.0061570	0.8669363	0.00616	**	NA
ASXL1	colorectal cancer	0.0061648	0.8669363	0.00616	**	NA
CCT8L2	colorectal cancer	0.0061648	0.8669363	0.00616	**	NA
MTMR14	colorectal cancer	0.0061648	0.8669363	0.00616	**	NA
TTC32	uterine cancer	0.0062881	0.8669363	0.00629	**	NA
NR4A1	lung cancer	0.0064934	0.8669363	0.00649	**	NA
SLC22A17	lung cancer	0.0064934	0.8669363	0.00649	**	NA
FAM208B	colorectal cancer	0.0065065	0.8669363	0.00651	**	NA
ROCK1	colorectal cancer	0.0066106	0.8669363	0.00661	**	NA
ZNF521	colorectal cancer	0.0066975	0.8669363	0.00670	**	NA
RFWD3	lung cancer	0.0067488	0.8669363	0.00675	**	NA
TYRP1	lung cancer	0.0067488	0.8669363	0.00675	**	NA
ADRBK2	uterine cancer	0.0067676	0.8669363	0.00677	**	NA
DVL2	uterine cancer	0.0067676	0.8669363	0.00677	**	NA
EXOC8	uterine cancer	0.0067676	0.8669363	0.00677	**	NA
ITSN1	colorectal cancer	0.0069403	0.8669363	0.00694	**	NA
ZNF292	colorectal cancer	0.0069403	0.8669363	0.00694	**	NA
MIS18BP1	colorectal cancer	0.0070098	0.8669363	0.00701	**	NA
OR5M8	colorectal cancer	0.0070184	0.8669363	0.00702	**	NA
PIK3CA	colorectal cancer	0.0070506	0.8669363	0.00705	**	NA
DDX11	lung cancer	0.0070952	0.8669363	0.00710	**	NA
KMT2C	multiple myeloma	0.0071541	0.8669363	0.00715	**	NA
MYH6	uterine cancer	0.0071786	0.8669363	0.00718	**	NA
ARID1B	ovarian cancer	0.0072055	0.8669363	0.00721	**	NA
SURF6	uterine cancer	0.0073058	0.8669363	0.00731	**	NA
C1orf86	leukemia	0.0073710	0.8669363	0.00737	**	NA
TEX10	ovarian cancer	0.0075601	0.8669363	0.00756	**	NA
ALPK3	ovarian cancer	0.0076300	0.8669363	0.00763	**	NA
MYOM3	lung cancer	0.0076435	0.8669363	0.00764	**	NA
PNPLA5	colorectal cancer	0.0077740	0.8669363	0.00777	**	NA
PTGFRN	lung cancer	0.0078691	0.8669363	0.00787	**	NA
PCDH10	uterine cancer	0.0078925	0.8669363	0.00789	**	NA
ANKRD23	colorectal cancer	0.0078965	0.8669363	0.00790	**	NA
HERC1	skin cancer	0.0079501	0.8669363	0.00795	**	NA
C12orf4	uterine cancer	0.0080215	0.8669363	0.00802	**	NA
EGFLAM	lung cancer	0.0081906	0.8669363	0.00819	**	NA
SPRED1	lung cancer	0.0084512	0.8669363	0.00845	**	NA
SBF2	lung cancer	0.0084541	0.8669363	0.00845	**	NA
EFCAB5	ovarian cancer	0.0084624	0.8669363	0.00846	**	NA
CSNK1D	uterine cancer	0.0085754	0.8669363	0.00858	**	NA
FAM110A	uterine cancer	0.0085754	0.8669363	0.00858	**	NA
MICAL1	uterine cancer	0.0085754	0.8669363	0.00858	**	NA
MORF4L1	uterine cancer	0.0085754	0.8669363	0.00858	**	NA
RIOK2	uterine cancer	0.0085754	0.8669363	0.00858	**	NA
GAA	colorectal cancer	0.0085960	0.8669363	0.00860	**	NA
KIAA1107	colorectal cancer	0.0085960	0.8669363	0.00860	**	NA
ZNF536	skin cancer	0.0086987	0.8669363	0.00870	**	NA
RPS6KA2	uterine cancer	0.0087779	0.8669363	0.00878	**	NA
SOGA1	lung cancer	0.0088239	0.8669363	0.00882	**	NA
TPR	lung cancer	0.0088831	0.8669363	0.00888	**	NA
SHANK1	central nervous system cancer	0.0088878	0.8669363	0.00889	**	NA
TECRL	lung cancer	0.0089331	0.8669363	0.00893	**	NA
SVEP1	skin cancer	0.0090238	0.8669363	0.00902	**	NA
DPYSL5	uterine cancer	0.0091517	0.8669363	0.00915	**	NA
FAM189A1	uterine cancer	0.0091517	0.8669363	0.00915	**	NA
IRX6	uterine cancer	0.0091517	0.8669363	0.00915	**	NA
XKR9	uterine cancer	0.0091517	0.8669363	0.00915	**	NA
KIAA0922	lung cancer	0.0091532	0.8669363	0.00915	**	NA
TTF1	lung cancer	0.0092125	0.8669363	0.00921	**	NA
TBC1D10B	uterine cancer	0.0092568	0.8669363	0.00926	**	NA
DNAJC8	uterine cancer	0.0092717	0.8669363	0.00927	**	NA
PKDCC	uterine cancer	0.0092717	0.8669363	0.00927	**	NA
TCF3	uterine cancer	0.0092717	0.8669363	0.00927	**	NA
ZNF207	uterine cancer	0.0093098	0.8669363	0.00931	**	NA
RASIP1	colorectal cancer	0.0093199	0.8669363	0.00932	**	NA
AP5B1	uterine cancer	0.0093215	0.8669363	0.00932	**	NA
RAD50	leukemia	0.0094090	0.8669363	0.00941	**	NA
KRT17	breast cancer	0.0094667	0.8669363	0.00947	**	NA
SCFD1	colorectal cancer	0.0094882	0.8669363	0.00949	**	NA
DNAH5	colorectal cancer	0.0095928	0.8669363	0.00959	**	NA
INTS4	uterine cancer	0.0096407	0.8669363	0.00964	**	NA
TTF1	leukemia	0.0097690	0.8669363	0.00977	**	NA
LRP4	uterine cancer	0.0099566	0.8669363	0.00996	**	NA
ZNF469	uterine cancer	0.0099581	0.8669363	0.00996	**	NA
IPO4	uterine cancer	0.0099688	0.8669363	0.00997	**	NA

wilcox_gene_delmis_lineage_plot <- ggplot(data = crispr_signif_delmis_lineage) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_gene_delmis_lineage_plot

5 Wilcoxon tests: All mutations

---

5.1 Grouped by gene

5.1.1 Deleterious vs. Other

crispr_signif_allmut_del <- compare_means(Score ~ Mutation_Status_Deleterious, group.by = c("Hugo_Symbol"), data = crispr_data, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_allmut_del <- adj_signif(crispr_signif_allmut_del)
crispr_signif_allmut_del <- crispr_signif_allmut_del[order(crispr_signif_allmut_del$p),]
saveRDS(crispr_signif_allmut_del, "./data_munging/rds/crispr_signif_allmut_deleterious_gene.rds")

# write.table(crispr_signif_allmut_del, file = "~/Desktop/crispr_signif_allmut_deleterious_gene.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_allmut_del <- readRDS("./data_munging/rds/crispr_signif_allmut_deleterious_gene.rds")

knitr::kable(filter(crispr_signif_allmut_del, p < 0.01)[, c("Hugo_Symbol", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing deleterious mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing deleterious mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	p	p.adj	p.format	p.signif	p.signif.adj
PTEN	0.0000000	0.0000000	2.9e-13	****	****
TP53	0.0000002	0.0016540	2.5e-07	****	**
ARID1A	0.0000011	0.0047700	1.1e-06	****	**
VHL	0.0000016	0.0053734	1.6e-06	****	**
UTP20	0.0000301	0.0802533	3.0e-05	****	NA
KRT19	0.0000705	0.1566873	7.0e-05	****	NA
ZC3H13	0.0009557	0.7440112	0.00096	***	NA
ARID1B	0.0010200	0.7440112	0.00102	**	NA
ABCD4	0.0012457	0.7440112	0.00125	**	NA
TCERG1	0.0012735	0.7440112	0.00127	**	NA
NPSR1	0.0013941	0.7440112	0.00139	**	NA
KRTAP10-6	0.0015323	0.7440112	0.00153	**	NA
PLXNA1	0.0016291	0.7440112	0.00163	**	NA
LILRB2	0.0016968	0.7440112	0.00170	**	NA
RNF208	0.0019385	0.7440112	0.00194	**	NA
AJAP1	0.0021018	0.7440112	0.00210	**	NA
HAX1	0.0022315	0.7440112	0.00223	**	NA
TIMD4	0.0022527	0.7440112	0.00225	**	NA
PIGR	0.0028924	0.7440112	0.00289	**	NA
TP53BP2	0.0029507	0.7440112	0.00295	**	NA
MSH6	0.0031226	0.7440112	0.00312	**	NA
KLHL17	0.0038240	0.7440112	0.00382	**	NA
TUBGCP5	0.0038993	0.7440112	0.00390	**	NA
FMN1	0.0039763	0.7440112	0.00398	**	NA
AKAP13	0.0040426	0.7440112	0.00404	**	NA
UGT2A3	0.0041569	0.7440112	0.00416	**	NA
BRD4	0.0042237	0.7440112	0.00422	**	NA
RB1	0.0042661	0.7440112	0.00427	**	NA
NIPBL	0.0042726	0.7440112	0.00427	**	NA
ATAD5	0.0045229	0.7440112	0.00452	**	NA
CR1	0.0047742	0.7440112	0.00477	**	NA
PPIL4	0.0047926	0.7440112	0.00479	**	NA
RINT1	0.0048906	0.7440112	0.00489	**	NA
SIN3A	0.0049114	0.7440112	0.00491	**	NA
PIK3R1	0.0052016	0.7440112	0.00520	**	NA
TPR	0.0052404	0.7440112	0.00524	**	NA
DLD	0.0053697	0.7440112	0.00537	**	NA
PTPRR	0.0055220	0.7440112	0.00552	**	NA
CSTF3	0.0055891	0.7440112	0.00559	**	NA
OLFML2B	0.0058315	0.7440112	0.00583	**	NA
GSTM5	0.0058384	0.7440112	0.00584	**	NA
NOC4L	0.0061581	0.7440112	0.00616	**	NA
KIAA1107	0.0061991	0.7440112	0.00620	**	NA
RTN3	0.0062371	0.7440112	0.00624	**	NA
PLOD3	0.0062880	0.7440112	0.00629	**	NA
ZNF439	0.0063457	0.7440112	0.00635	**	NA
DMKN	0.0063484	0.7440112	0.00635	**	NA
EDNRB	0.0063517	0.7440112	0.00635	**	NA
UTP3	0.0065359	0.7440112	0.00654	**	NA
IQCH	0.0067700	0.7440112	0.00677	**	NA
ST7	0.0068047	0.7440112	0.00680	**	NA
ZNF177	0.0068619	0.7440112	0.00686	**	NA
ENAH	0.0069381	0.7440112	0.00694	**	NA
RTF1	0.0070416	0.7440112	0.00704	**	NA
UTS2B	0.0072533	0.7440112	0.00725	**	NA
TRIM13	0.0073672	0.7440112	0.00737	**	NA
KLHL1	0.0073975	0.7440112	0.00740	**	NA
AMER2	0.0076915	0.7440112	0.00769	**	NA
DMWD	0.0077073	0.7440112	0.00771	**	NA
ATG2A	0.0077283	0.7440112	0.00773	**	NA
NPAT	0.0078418	0.7440112	0.00784	**	NA
SMARCB1	0.0081997	0.7440112	0.00820	**	NA
PAQR3	0.0082276	0.7440112	0.00823	**	NA
SF3B2	0.0084940	0.7440112	0.00849	**	NA
NGRN	0.0085338	0.7440112	0.00853	**	NA
SKOR1	0.0085338	0.7440112	0.00853	**	NA
PHLPP1	0.0085991	0.7440112	0.00860	**	NA
ZBTB25	0.0086381	0.7440112	0.00864	**	NA
ZFR	0.0087353	0.7440112	0.00874	**	NA
ZNF124	0.0089578	0.7440112	0.00896	**	NA
TOP1MT	0.0089680	0.7440112	0.00897	**	NA
NUP98	0.0091458	0.7440112	0.00915	**	NA
THEMIS	0.0092069	0.7440112	0.00921	**	NA
ESYT2	0.0092528	0.7440112	0.00925	**	NA
DZANK1	0.0092793	0.7440112	0.00928	**	NA
SRPR	0.0092882	0.7440112	0.00929	**	NA
PAX5	0.0093106	0.7440112	0.00931	**	NA
ST5	0.0094802	0.7440112	0.00948	**	NA
TTC22	0.0094965	0.7440112	0.00950	**	NA
BUB1	0.0095144	0.7440112	0.00951	**	NA
RIMBP3	0.0096462	0.7440112	0.00965	**	NA

wilcox_gene_allmut_plot <- ggplot(data = crispr_signif_allmut_del) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_gene_allmut_plot

# ggsave(filename = "./plots_18Q3/crispr/pvals_genes.pdf", plot = wilcox_gene_plot, width = 8, height = 4, device = "pdf")

5.1.2 Non-silent mutant vs. Other

crispr_signif_allmut_nonsilent <- compare_means(Score ~ Mutation_Status_Nonsilent, group.by = c("Hugo_Symbol"), data = crispr_data, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_allmut_nonsilent <- adj_signif(crispr_signif_allmut_nonsilent)
crispr_signif_allmut_nonsilent <- crispr_signif_allmut_nonsilent[order(crispr_signif_allmut_nonsilent$p),]
saveRDS(crispr_signif_allmut_nonsilent, "./data_munging/rds/crispr_signif_allmut_nonsilent_gene.rds")

# write.table(crispr_signif_allmut_nonsilent, file = "~/Desktop/crispr_signif_allmut_nonsilent_gene.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_allmut_nonsilent <- readRDS("./data_munging/rds/crispr_signif_allmut_nonsilent_gene.rds")

knitr::kable(filter(crispr_signif_allmut_nonsilent, p < 0.01)[, c("Hugo_Symbol", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing non-silent mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing non-silent mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	p	p.adj	p.format	p.signif	p.signif.adj
TP53	0.0000000	0.0000000	< 2e-16	****	****
KRAS	0.0000000	0.0000000	< 2e-16	****	****
NRAS	0.0000000	0.0000000	< 2e-16	****	****
BRAF	0.0000000	0.0000000	< 2e-16	****	****
PTEN	0.0000000	0.0000000	< 2e-16	****	****
PIK3CA	0.0000000	0.0000000	1.0e-13	****	****
PIK3R1	0.0000001	0.0003379	1.4e-07	****	***
CTNNB1	0.0000023	0.0050434	2.3e-06	****	**
TCERG1	0.0000055	0.0104819	5.5e-06	****
ARID1A	0.0000065	0.0111737	6.5e-06	****
TPR	0.0000510	0.0797535	5.1e-05	****	NA
VHL	0.0000665	0.0952975	6.7e-05	****	NA
FCGBP	0.0000895	0.1184104	9.0e-05	****	NA
ZNF177	0.0001226	0.1505314	0.00012	***	NA
C14orf39	0.0002001	0.2293087	0.00020	***	NA
SLC22A9	0.0002503	0.2677702	0.00025	***	NA
GSTM5	0.0002648	0.2677702	0.00026	***	NA
NIPBL	0.0003016	0.2880836	0.00030	***	NA
PIGW	0.0003638	0.3291939	0.00036	***	NA
TLX2	0.0004787	0.4114775	0.00048	***	NA
ARFGAP1	0.0005157	0.4159808	0.00052	***	NA
ZNF808	0.0005323	0.4159808	0.00053	***	NA
CD320	0.0005816	0.4347206	0.00058	***	NA
ING2	0.0006989	0.4568910	0.00070	***	NA
MAT2B	0.0007184	0.4568910	0.00072	***	NA
SYNPO2L	0.0007699	0.4568910	0.00077	***	NA
UTP20	0.0007718	0.4568910	0.00077	***	NA
HRAS	0.0008408	0.4568910	0.00084	***	NA
TAOK2	0.0008437	0.4568910	0.00084	***	NA
CPSF1	0.0008505	0.4568910	0.00085	***	NA
UTP3	0.0008549	0.4568910	0.00085	***	NA
RFC1	0.0008787	0.4568910	0.00088	***	NA
RNF208	0.0008907	0.4568910	0.00089	***	NA
KHSRP	0.0009036	0.4568910	0.00090	***	NA
KCNIP4	0.0009472	0.4652404	0.00095	***	NA
GOLGA3	0.0010340	0.4841935	0.00103	**	NA
PROM1	0.0010485	0.4841935	0.00105	**	NA
PMPCA	0.0010990	0.4841935	0.00110	**	NA
MDN1	0.0011415	0.4841935	0.00114	**	NA
PCDHA8	0.0012404	0.4841935	0.00124	**	NA
OR13C4	0.0012702	0.4841935	0.00127	**	NA
FASTKD2	0.0012728	0.4841935	0.00127	**	NA
TELO2	0.0012922	0.4841935	0.00129	**	NA
TAS1R2	0.0013163	0.4841935	0.00132	**	NA
ZNF439	0.0013227	0.4841935	0.00132	**	NA
KRT19	0.0013501	0.4841935	0.00135	**	NA
AVEN	0.0013562	0.4841935	0.00136	**	NA
MTMR2	0.0014414	0.4841935	0.00144	**	NA
E2F1	0.0014486	0.4841935	0.00145	**	NA
IQCH	0.0014602	0.4841935	0.00146	**	NA
LPO	0.0014636	0.4841935	0.00146	**	NA
FRMD4B	0.0014758	0.4841935	0.00148	**	NA
PLA2G4F	0.0014997	0.4841935	0.00150	**	NA
DSEL	0.0015209	0.4841935	0.00152	**	NA
HSD3B7	0.0015616	0.4880853	0.00156	**	NA
PCDHB15	0.0016370	0.4937603	0.00164	**	NA
TAAR1	0.0016765	0.4937603	0.00168	**	NA
MYH13	0.0016962	0.4937603	0.00170	**	NA
ACSM2B	0.0017107	0.4937603	0.00171	**	NA
OR8D1	0.0017233	0.4937603	0.00172	**	NA
KIAA1211L	0.0019402	0.5370893	0.00194	**	NA
SENP8	0.0019559	0.5370893	0.00196	**	NA
RUVBL1	0.0019950	0.5370893	0.00200	**	NA
OR52E8	0.0020406	0.5370893	0.00204	**	NA
CNOT1	0.0020488	0.5370893	0.00205	**	NA
PI4K2A	0.0020961	0.5370893	0.00210	**	NA
KPNA6	0.0021334	0.5370893	0.00213	**	NA
ST6GALNAC1	0.0022068	0.5370893	0.00221	**	NA
POU2F1	0.0022102	0.5370893	0.00221	**	NA
BTBD11	0.0022318	0.5370893	0.00223	**	NA
LPCAT4	0.0022875	0.5370893	0.00229	**	NA
LILRB2	0.0023004	0.5370893	0.00230	**	NA
ANKRD31	0.0023475	0.5370893	0.00235	**	NA
OR51T1	0.0023614	0.5370893	0.00236	**	NA
METTL17	0.0023923	0.5370893	0.00239	**	NA
POLG	0.0024034	0.5370893	0.00240	**	NA
CIITA	0.0024057	0.5370893	0.00241	**	NA
ADAM15	0.0024806	0.5467237	0.00248	**	NA
RAB43	0.0025433	0.5500972	0.00254	**	NA
EZH2	0.0025733	0.5500972	0.00257	**	NA
ZDHHC24	0.0025919	0.5500972	0.00259	**	NA
NFE2L2	0.0026889	0.5525281	0.00269	**	NA
SURF6	0.0027361	0.5525281	0.00274	**	NA
KIF11	0.0027512	0.5525281	0.00275	**	NA
SDHD	0.0027619	0.5525281	0.00276	**	NA
GRM7	0.0027641	0.5525281	0.00276	**	NA
NXPH4	0.0028292	0.5590491	0.00283	**	NA
DENND4C	0.0028765	0.5604565	0.00288	**	NA
LRGUK	0.0029016	0.5604565	0.00290	**	NA
SAMM50	0.0030102	0.5719308	0.00301	**	NA
ACTA1	0.0030465	0.5719308	0.00305	**	NA
SPAG17	0.0030697	0.5719308	0.00307	**	NA
SLC26A2	0.0030940	0.5719308	0.00309	**	NA
MAP2K3	0.0032831	0.5896613	0.00328	**	NA
DIS3L2	0.0032847	0.5896613	0.00328	**	NA
PTPRE	0.0032929	0.5896613	0.00329	**	NA
SCG2	0.0034839	0.6121167	0.00348	**	NA
TRIM8	0.0034895	0.6121167	0.00349	**	NA
CAMK2B	0.0035496	0.6128833	0.00355	**	NA
SLC38A7	0.0036411	0.6128833	0.00364	**	NA
MMRN2	0.0036540	0.6128833	0.00365	**	NA
MAML2	0.0037079	0.6128833	0.00371	**	NA
SGCD	0.0037645	0.6128833	0.00376	**	NA
FBXW7	0.0037715	0.6128833	0.00377	**	NA
ATXN2	0.0037776	0.6128833	0.00378	**	NA
VPS13D	0.0037846	0.6128833	0.00378	**	NA
KRT83	0.0038147	0.6128833	0.00381	**	NA
SUSD5	0.0039261	0.6249422	0.00393	**	NA
ATR	0.0040408	0.6288252	0.00404	**	NA
ATXN2L	0.0041364	0.6288252	0.00414	**	NA
CD83	0.0041819	0.6288252	0.00418	**	NA
ZNF135	0.0042047	0.6288252	0.00420	**	NA
CREBBP	0.0042381	0.6288252	0.00424	**	NA
TOP1MT	0.0042412	0.6288252	0.00424	**	NA
EMILIN3	0.0042659	0.6288252	0.00427	**	NA
SPTBN4	0.0042799	0.6288252	0.00428	**	NA
SPHK2	0.0043100	0.6288252	0.00431	**	NA
GNAI2	0.0043171	0.6288252	0.00432	**	NA
PSMB4	0.0043587	0.6288252	0.00436	**	NA
TPP1	0.0046001	0.6288252	0.00460	**	NA
NFE2L1	0.0046446	0.6288252	0.00464	**	NA
PIGP	0.0046922	0.6288252	0.00469	**	NA
PPP1R1C	0.0047398	0.6288252	0.00474	**	NA
CDC37	0.0047810	0.6288252	0.00478	**	NA
TFAP2A	0.0048201	0.6288252	0.00482	**	NA
CD200R1	0.0048862	0.6288252	0.00489	**	NA
CWH43	0.0048913	0.6288252	0.00489	**	NA
FOXRED1	0.0049144	0.6288252	0.00491	**	NA
HCRTR1	0.0049160	0.6288252	0.00492	**	NA
CACNA1I	0.0050408	0.6288252	0.00504	**	NA
RBBP9	0.0050826	0.6288252	0.00508	**	NA
OGFOD3	0.0051338	0.6288252	0.00513	**	NA
AKR1C1	0.0051682	0.6288252	0.00517	**	NA
TBC1D22A	0.0052429	0.6288252	0.00524	**	NA
APOBEC1	0.0052779	0.6288252	0.00528	**	NA
OR56A3	0.0052916	0.6288252	0.00529	**	NA
SLC46A2	0.0053108	0.6288252	0.00531	**	NA
STK17B	0.0053176	0.6288252	0.00532	**	NA
C6orf15	0.0053410	0.6288252	0.00534	**	NA
SMPD1	0.0053513	0.6288252	0.00535	**	NA
FBXW12	0.0053691	0.6288252	0.00537	**	NA
MGA	0.0053870	0.6288252	0.00539	**	NA
RSPH6A	0.0053903	0.6288252	0.00539	**	NA
EEF2	0.0054341	0.6288252	0.00543	**	NA
CD5L	0.0054356	0.6288252	0.00544	**	NA
AKR1B15	0.0054791	0.6288252	0.00548	**	NA
THADA	0.0055256	0.6288252	0.00553	**	NA
MYOC	0.0055382	0.6288252	0.00554	**	NA
SLC12A4	0.0056227	0.6288252	0.00562	**	NA
DNAJC5B	0.0057016	0.6288252	0.00570	**	NA
TAS2R60	0.0057034	0.6288252	0.00570	**	NA
IBA57	0.0057420	0.6288252	0.00574	**	NA
HDGFRP2	0.0057596	0.6288252	0.00576	**	NA
MRPS34	0.0057928	0.6288252	0.00579	**	NA
AP5B1	0.0057997	0.6288252	0.00580	**	NA
KIF3B	0.0058153	0.6288252	0.00582	**	NA
SSH2	0.0058405	0.6288252	0.00584	**	NA
MBD3L2	0.0058844	0.6288252	0.00588	**	NA
COPS2	0.0059315	0.6288252	0.00593	**	NA
WDR75	0.0059969	0.6288252	0.00600	**	NA
FRYL	0.0060235	0.6288252	0.00602	**	NA
ZNF438	0.0060372	0.6288252	0.00604	**	NA
ELK3	0.0061135	0.6288252	0.00611	**	NA
MUS81	0.0061273	0.6288252	0.00613	**	NA
PRRC1	0.0061280	0.6288252	0.00613	**	NA
CLEC9A	0.0062087	0.6288252	0.00621	**	NA
LMX1A	0.0062097	0.6288252	0.00621	**	NA
SFXN3	0.0062354	0.6288252	0.00624	**	NA
FAM181B	0.0062849	0.6288252	0.00628	**	NA
SMARCB1	0.0062993	0.6288252	0.00630	**	NA
ACBD6	0.0063036	0.6288252	0.00630	**	NA
SUPT7L	0.0063204	0.6288252	0.00632	**	NA
CYP19A1	0.0063281	0.6288252	0.00633	**	NA
FBXL20	0.0064106	0.6333572	0.00641	**	NA
OR4N2	0.0065455	0.6387591	0.00655	**	NA
MIIP	0.0066145	0.6387591	0.00661	**	NA
FCN3	0.0066248	0.6387591	0.00662	**	NA
ZNF107	0.0066752	0.6387591	0.00668	**	NA
MLST8	0.0067360	0.6387591	0.00674	**	NA
TSPAN13	0.0067540	0.6387591	0.00675	**	NA
DPP7	0.0067839	0.6387591	0.00678	**	NA
KDM5B	0.0068837	0.6387591	0.00688	**	NA
IFFO2	0.0068857	0.6387591	0.00689	**	NA
COG3	0.0069083	0.6387591	0.00691	**	NA
DHX35	0.0069214	0.6387591	0.00692	**	NA
PPM1A	0.0069353	0.6387591	0.00694	**	NA
MSGN1	0.0069483	0.6387591	0.00695	**	NA
ANKRD32	0.0071033	0.6427900	0.00710	**	NA
TLN1	0.0071319	0.6427900	0.00713	**	NA
POC1A	0.0071368	0.6427900	0.00714	**	NA
CLDN5	0.0071709	0.6427900	0.00717	**	NA
PRKCZ	0.0072554	0.6427900	0.00726	**	NA
ACTL8	0.0072969	0.6427900	0.00730	**	NA
KRTAP10-6	0.0072992	0.6427900	0.00730	**	NA
SMCR8	0.0073359	0.6427900	0.00734	**	NA
OLFML2B	0.0073612	0.6427900	0.00736	**	NA
HSPB2	0.0073660	0.6427900	0.00737	**	NA
INTS12	0.0075473	0.6534174	0.00755	**	NA
NAA15	0.0075638	0.6534174	0.00756	**	NA
ARSB	0.0076069	0.6538525	0.00761	**	NA
VPS37B	0.0076704	0.6545014	0.00767	**	NA
CCDC159	0.0077369	0.6545014	0.00774	**	NA
SSH1	0.0077665	0.6545014	0.00777	**	NA
NCR3LG1	0.0078580	0.6545014	0.00786	**	NA
ACYP2	0.0079841	0.6545014	0.00798	**	NA
XPO5	0.0080510	0.6545014	0.00805	**	NA
GTF3C1	0.0080700	0.6545014	0.00807	**	NA
OR4S2	0.0081035	0.6545014	0.00810	**	NA
BTAF1	0.0081559	0.6545014	0.00816	**	NA
TACSTD2	0.0081791	0.6545014	0.00818	**	NA
MED30	0.0082419	0.6545014	0.00824	**	NA
ADAM32	0.0082522	0.6545014	0.00825	**	NA
LY9	0.0083045	0.6545014	0.00830	**	NA
H2AFY2	0.0083475	0.6545014	0.00835	**	NA
MRPL13	0.0083762	0.6545014	0.00838	**	NA
PAQR3	0.0084147	0.6545014	0.00841	**	NA
GHITM	0.0084474	0.6545014	0.00845	**	NA
SGK2	0.0084586	0.6545014	0.00846	**	NA
ADO	0.0085378	0.6545014	0.00854	**	NA
ZNF17	0.0085562	0.6545014	0.00856	**	NA
MFAP4	0.0085654	0.6545014	0.00857	**	NA
CD163	0.0085663	0.6545014	0.00857	**	NA
COL7A1	0.0085733	0.6545014	0.00857	**	NA
CD80	0.0085983	0.6545014	0.00860	**	NA
ARMC7	0.0085988	0.6545014	0.00860	**	NA
COL8A1	0.0086043	0.6545014	0.00860	**	NA
KHDC1L	0.0086562	0.6546529	0.00866	**	NA
CHD2	0.0086825	0.6546529	0.00868	**	NA
PLCH2	0.0088368	0.6560317	0.00884	**	NA
OR13C3	0.0088398	0.6560317	0.00884	**	NA
C1orf141	0.0089498	0.6560317	0.00895	**	NA
ARHGEF17	0.0089894	0.6560317	0.00899	**	NA
ARID1B	0.0090009	0.6560317	0.00900	**	NA
COL9A2	0.0090078	0.6560317	0.00901	**	NA
ZC3H4	0.0091088	0.6560317	0.00911	**	NA
SUPT6H	0.0091374	0.6560317	0.00914	**	NA
CCNL1	0.0091597	0.6560317	0.00916	**	NA
TMEM258	0.0091769	0.6560317	0.00918	**	NA
USP32	0.0092096	0.6560317	0.00921	**	NA
DNAJC8	0.0093058	0.6560317	0.00931	**	NA
C20orf26	0.0093466	0.6560317	0.00935	**	NA
KRTAP4-4	0.0093494	0.6560317	0.00935	**	NA
ACHE	0.0093636	0.6560317	0.00936	**	NA
LCTL	0.0093837	0.6560317	0.00938	**	NA
ELMSAN1	0.0093954	0.6560317	0.00940	**	NA
SLC25A4	0.0094344	0.6560317	0.00943	**	NA
F11R	0.0094708	0.6560317	0.00947	**	NA
LY6G6F	0.0095144	0.6560317	0.00951	**	NA
ZNF330	0.0095171	0.6560317	0.00952	**	NA
NECAB1	0.0095689	0.6560317	0.00957	**	NA
GMCL1	0.0096195	0.6560317	0.00962	**	NA
C16orf58	0.0096729	0.6560317	0.00967	**	NA
ZBTB44	0.0096904	0.6560317	0.00969	**	NA
INHBA	0.0097282	0.6560317	0.00973	**	NA
CLEC4C	0.0097545	0.6560317	0.00975	**	NA
GLG1	0.0097693	0.6560317	0.00977	**	NA
RNF31	0.0098119	0.6563315	0.00981	**	NA
COPS3	0.0098996	0.6577057	0.00990	**	NA
NOL6	0.0099717	0.6577057	0.00997	**	NA
WDR77	0.0099778	0.6577057	0.00998	**	NA

wilcox_gene_allmut_nonsilent_plot <- ggplot(data = crispr_signif_allmut_nonsilent) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_gene_allmut_nonsilent_plot

5.1.3 Deleterious and missense mutant vs. Other

crispr_signif_allmut_delmis <- compare_means(Score ~ Mutation_Status_DeleteriousMissense, group.by = c("Hugo_Symbol"), data = crispr_data, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_allmut_delmis <- adj_signif(crispr_signif_allmut_delmis)
crispr_signif_allmut_delmis <- crispr_signif_allmut_delmis[order(crispr_signif_allmut_delmis$p),]
saveRDS(crispr_signif_allmut_delmis, "./data_munging/rds/crispr_signif_allmut_deleteriousmissense_gene.rds")

# write.table(crispr_signif_allmut_delmis, file = "~/Desktop/crispr_signif_allmut_deleteriousmissense_gene.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_allmut_delmis <- readRDS("./data_munging/rds/crispr_signif_allmut_deleteriousmissense_gene.rds")

knitr::kable(filter(crispr_signif_allmut_delmis, p < 0.01)[, c("Hugo_Symbol", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing deleterious and missense mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing deleterious and missense mutant vs other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	p	p.adj	p.format	p.signif	p.signif.adj
KRAS	0.0000000	0.0000000	< 2e-16	****	****
TP53	0.0000000	0.0000000	< 2e-16	****	****
BRAF	0.0000000	0.0000000	< 2e-16	****	****
NRAS	0.0000000	0.0000000	< 2e-16	****	****
PTEN	0.0000000	0.0000000	5.1e-16	****	****
PIK3CA	0.0000000	0.0000000	9.7e-14	****	****
CTNNB1	0.0000023	0.0057622	2.3e-06	****	**
TCERG1	0.0000043	0.0092556	4.3e-06	****	**
ARID1A	0.0000077	0.0146617	7.7e-06	****
TPR	0.0000436	0.0749151	4.4e-05	****	NA
FCGBP	0.0000695	0.1085679	6.9e-05	****	NA
VHL	0.0001029	0.1473663	0.00010	***	NA
ZNF177	0.0001226	0.1620635	0.00012	***	NA
C14orf39	0.0002001	0.2456164	0.00020	***	NA
SLC22A9	0.0002503	0.2844231	0.00025	***	NA
GSTM5	0.0002648	0.2844231	0.00026	***	NA
PIGW	0.0003638	0.3678156	0.00036	***	NA
TLX2	0.0004787	0.4570643	0.00048	***	NA
ARFGAP1	0.0005157	0.4574458	0.00052	***	NA
ZNF808	0.0005323	0.4574458	0.00053	***	NA
CD320	0.0005816	0.4759840	0.00058	***	NA
ING2	0.0006989	0.4783606	0.00070	***	NA
NIPBL	0.0007160	0.4783606	0.00072	***	NA
MAT2B	0.0007184	0.4783606	0.00072	***	NA
SYNPO2L	0.0007699	0.4783606	0.00077	***	NA
UTP20	0.0007718	0.4783606	0.00077	***	NA
HRAS	0.0008408	0.4783606	0.00084	***	NA
CPSF1	0.0008505	0.4783606	0.00085	***	NA
UTP3	0.0008549	0.4783606	0.00085	***	NA
FBXW7	0.0008732	0.4783606	0.00087	***	NA
RFC1	0.0008787	0.4783606	0.00088	***	NA
RNF208	0.0008907	0.4783606	0.00089	***	NA
KCNIP4	0.0009472	0.4932932	0.00095	***	NA
GOLGA3	0.0010340	0.5125264	0.00103	**	NA
PROM1	0.0010485	0.5125264	0.00105	**	NA
PMPCA	0.0010990	0.5125264	0.00110	**	NA
PIK3R1	0.0011525	0.5125264	0.00115	**	NA
PCDHA8	0.0012404	0.5125264	0.00124	**	NA
OR13C4	0.0012702	0.5125264	0.00127	**	NA
MDN1	0.0012746	0.5125264	0.00127	**	NA
TELO2	0.0012922	0.5125264	0.00129	**	NA
TAS1R2	0.0013163	0.5125264	0.00132	**	NA
ZNF439	0.0013227	0.5125264	0.00132	**	NA
KRT19	0.0013501	0.5125264	0.00135	**	NA
MTMR2	0.0014414	0.5125264	0.00144	**	NA
E2F1	0.0014486	0.5125264	0.00145	**	NA
IQCH	0.0014602	0.5125264	0.00146	**	NA
LPO	0.0014636	0.5125264	0.00146	**	NA
FRMD4B	0.0014758	0.5125264	0.00148	**	NA
PLA2G4F	0.0014997	0.5125264	0.00150	**	NA
DSEL	0.0015209	0.5125264	0.00152	**	NA
HSD3B7	0.0015616	0.5160939	0.00156	**	NA
PCDHB15	0.0016370	0.5195965	0.00164	**	NA
TAAR1	0.0016765	0.5195965	0.00168	**	NA
MYH13	0.0016962	0.5195965	0.00170	**	NA
ACSM2B	0.0017107	0.5195965	0.00171	**	NA
OR8D1	0.0017233	0.5195965	0.00172	**	NA
KIAA1211L	0.0019402	0.5430002	0.00194	**	NA
SENP8	0.0019559	0.5430002	0.00196	**	NA
AVEN	0.0019832	0.5430002	0.00198	**	NA
TAOK2	0.0019841	0.5430002	0.00198	**	NA
RUVBL1	0.0019950	0.5430002	0.00200	**	NA
CLEC4C	0.0020406	0.5430002	0.00204	**	NA
OR52E8	0.0020406	0.5430002	0.00204	**	NA
PI4K2A	0.0020961	0.5430002	0.00210	**	NA
KPNA6	0.0021334	0.5430002	0.00213	**	NA
ST6GALNAC1	0.0022068	0.5430002	0.00221	**	NA
POU2F1	0.0022102	0.5430002	0.00221	**	NA
EZH2	0.0022226	0.5430002	0.00222	**	NA
BTBD11	0.0022318	0.5430002	0.00223	**	NA
LPCAT4	0.0022875	0.5430002	0.00229	**	NA
ANKRD31	0.0023475	0.5430002	0.00235	**	NA
OR51T1	0.0023614	0.5430002	0.00236	**	NA
METTL17	0.0023923	0.5430002	0.00239	**	NA
KHSRP	0.0023925	0.5430002	0.00239	**	NA
CIITA	0.0024057	0.5430002	0.00241	**	NA
TUBB2A	0.0024329	0.5430002	0.00243	**	NA
ADAM15	0.0024806	0.5465647	0.00248	**	NA
ZDHHC24	0.0025919	0.5638596	0.00259	**	NA
SURF6	0.0027361	0.5723325	0.00274	**	NA
KIF11	0.0027512	0.5723325	0.00275	**	NA
SDHD	0.0027619	0.5723325	0.00276	**	NA
GRM7	0.0027641	0.5723325	0.00276	**	NA
NXPH4	0.0028292	0.5788467	0.00283	**	NA
SAMM50	0.0030102	0.6042511	0.00301	**	NA
ACTA1	0.0030465	0.6042511	0.00305	**	NA
SPAG17	0.0030697	0.6042511	0.00307	**	NA
SLC26A2	0.0030940	0.6042511	0.00309	**	NA
DENND4C	0.0031465	0.6075857	0.00315	**	NA
ATXN2	0.0032463	0.6085056	0.00325	**	NA
MAP2K3	0.0032831	0.6085056	0.00328	**	NA
DIS3L2	0.0032847	0.6085056	0.00328	**	NA
PTPRE	0.0032929	0.6085056	0.00329	**	NA
CNOT1	0.0034549	0.6246874	0.00345	**	NA
SCG2	0.0034839	0.6246874	0.00348	**	NA
TRIM8	0.0034895	0.6246874	0.00349	**	NA
CAMK2B	0.0035496	0.6288942	0.00355	**	NA
SLC38A7	0.0036411	0.6335632	0.00364	**	NA
MMRN2	0.0036540	0.6335632	0.00365	**	NA
SGCD	0.0037645	0.6335632	0.00376	**	NA
VPS13D	0.0037846	0.6335632	0.00378	**	NA
KRT83	0.0038147	0.6335632	0.00381	**	NA
EEF2	0.0038279	0.6335632	0.00383	**	NA
LILRB2	0.0038340	0.6335632	0.00383	**	NA
SUSD5	0.0039261	0.6376846	0.00393	**	NA
NOL7	0.0039331	0.6376846	0.00393	**	NA
ATR	0.0040408	0.6473519	0.00404	**	NA
ATXN2L	0.0041364	0.6473519	0.00414	**	NA
CD83	0.0041819	0.6473519	0.00418	**	NA
ZNF135	0.0042047	0.6473519	0.00420	**	NA
TOP1MT	0.0042412	0.6473519	0.00424	**	NA
EMILIN3	0.0042659	0.6473519	0.00427	**	NA
SPTBN4	0.0042799	0.6473519	0.00428	**	NA
SPHK2	0.0043100	0.6473519	0.00431	**	NA
PSMB4	0.0043587	0.6473519	0.00436	**	NA
IQGAP3	0.0045407	0.6473519	0.00454	**	NA
TPP1	0.0046001	0.6473519	0.00460	**	NA
NFE2L1	0.0046446	0.6473519	0.00464	**	NA
PIGP	0.0046922	0.6473519	0.00469	**	NA
PPP1R1C	0.0047398	0.6473519	0.00474	**	NA
CDC37	0.0047810	0.6473519	0.00478	**	NA
TFAP2A	0.0048201	0.6473519	0.00482	**	NA
CD200R1	0.0048862	0.6473519	0.00489	**	NA
CWH43	0.0048913	0.6473519	0.00489	**	NA
FOXRED1	0.0049144	0.6473519	0.00491	**	NA
HCRTR1	0.0049160	0.6473519	0.00492	**	NA
RBBP9	0.0050826	0.6473519	0.00508	**	NA
OGFOD3	0.0051338	0.6473519	0.00513	**	NA
AKR1C1	0.0051682	0.6473519	0.00517	**	NA
TBC1D22A	0.0052429	0.6473519	0.00524	**	NA
APOBEC1	0.0052779	0.6473519	0.00528	**	NA
OR56A3	0.0052916	0.6473519	0.00529	**	NA
SLC46A2	0.0053108	0.6473519	0.00531	**	NA
C6orf15	0.0053410	0.6473519	0.00534	**	NA
SMPD1	0.0053513	0.6473519	0.00535	**	NA
FBXW12	0.0053691	0.6473519	0.00537	**	NA
MGA	0.0053870	0.6473519	0.00539	**	NA
RSPH6A	0.0053903	0.6473519	0.00539	**	NA
THADA	0.0055256	0.6473519	0.00553	**	NA
MYOC	0.0055382	0.6473519	0.00554	**	NA
LRGUK	0.0056014	0.6473519	0.00560	**	NA
SLC12A4	0.0056227	0.6473519	0.00562	**	NA
DNAJC5B	0.0057016	0.6473519	0.00570	**	NA
TAS2R60	0.0057034	0.6473519	0.00570	**	NA
IBA57	0.0057420	0.6473519	0.00574	**	NA
HDGFRP2	0.0057596	0.6473519	0.00576	**	NA
MRPS34	0.0057928	0.6473519	0.00579	**	NA
KIF3B	0.0058153	0.6473519	0.00582	**	NA
SSH2	0.0058405	0.6473519	0.00584	**	NA
MBD3L2	0.0058844	0.6473519	0.00588	**	NA
COPS2	0.0059315	0.6473519	0.00593	**	NA
WDR75	0.0059969	0.6473519	0.00600	**	NA
FRYL	0.0060235	0.6473519	0.00602	**	NA
ZNF438	0.0060372	0.6473519	0.00604	**	NA
MMS22L	0.0060571	0.6473519	0.00606	**	NA
ELK3	0.0061135	0.6473519	0.00611	**	NA
MUS81	0.0061273	0.6473519	0.00613	**	NA
PRRC1	0.0061280	0.6473519	0.00613	**	NA
CD5L	0.0061987	0.6473519	0.00620	**	NA
CLEC9A	0.0062087	0.6473519	0.00621	**	NA
LMX1A	0.0062097	0.6473519	0.00621	**	NA
SFXN3	0.0062354	0.6473519	0.00624	**	NA
RAB43	0.0062666	0.6473519	0.00627	**	NA
FAM181B	0.0062849	0.6473519	0.00628	**	NA
SMARCB1	0.0062993	0.6473519	0.00630	**	NA
ACBD6	0.0063036	0.6473519	0.00630	**	NA
SUPT7L	0.0063204	0.6473519	0.00632	**	NA
CYP19A1	0.0063281	0.6473519	0.00633	**	NA
FBXL20	0.0064106	0.6511943	0.00641	**	NA
CEP76	0.0064716	0.6511943	0.00647	**	NA
DPP7	0.0064794	0.6511943	0.00648	**	NA
OR4N2	0.0065455	0.6540139	0.00655	**	NA
MIIP	0.0066145	0.6543288	0.00661	**	NA
FCN3	0.0066248	0.6543288	0.00662	**	NA
ZNF107	0.0066752	0.6555409	0.00668	**	NA
TSPAN13	0.0067540	0.6595153	0.00675	**	NA
KDM5B	0.0068837	0.6597415	0.00688	**	NA
IFFO2	0.0068857	0.6597415	0.00689	**	NA
COG3	0.0069083	0.6597415	0.00691	**	NA
DHX35	0.0069214	0.6597415	0.00692	**	NA
MSGN1	0.0069483	0.6597415	0.00695	**	NA
ANKRD32	0.0071033	0.6599783	0.00710	**	NA
RB1	0.0071617	0.6599783	0.00716	**	NA
CLDN5	0.0071709	0.6599783	0.00717	**	NA
PRKCZ	0.0072554	0.6599783	0.00726	**	NA
ARID1B	0.0072590	0.6599783	0.00726	**	NA
ACTL8	0.0072969	0.6599783	0.00730	**	NA
KRTAP10-6	0.0072992	0.6599783	0.00730	**	NA
EML1	0.0073078	0.6599783	0.00731	**	NA
SMCR8	0.0073359	0.6599783	0.00734	**	NA
OLFML2B	0.0073612	0.6599783	0.00736	**	NA
CREBBP	0.0073732	0.6599783	0.00737	**	NA
F11R	0.0075268	0.6631134	0.00753	**	NA
INTS12	0.0075473	0.6631134	0.00755	**	NA
NAA15	0.0075638	0.6631134	0.00756	**	NA
ARSB	0.0076069	0.6631134	0.00761	**	NA
VPS37B	0.0076704	0.6631134	0.00767	**	NA
CCDC159	0.0077369	0.6631134	0.00774	**	NA
SSH1	0.0077665	0.6631134	0.00777	**	NA
NCR3LG1	0.0078580	0.6631134	0.00786	**	NA
PLOD1	0.0078951	0.6631134	0.00790	**	NA
ACYP2	0.0079841	0.6631134	0.00798	**	NA
XPO5	0.0080510	0.6631134	0.00805	**	NA
AP5B1	0.0080810	0.6631134	0.00808	**	NA
OR4S2	0.0081035	0.6631134	0.00810	**	NA
BTAF1	0.0081559	0.6631134	0.00816	**	NA
TACSTD2	0.0081791	0.6631134	0.00818	**	NA
MED30	0.0082419	0.6631134	0.00824	**	NA
ADAM32	0.0082522	0.6631134	0.00825	**	NA
LY9	0.0083045	0.6631134	0.00830	**	NA
H2AFY2	0.0083475	0.6631134	0.00835	**	NA
MRPL13	0.0083762	0.6631134	0.00838	**	NA
PAQR3	0.0084147	0.6631134	0.00841	**	NA
YLPM1	0.0084185	0.6631134	0.00842	**	NA
GHITM	0.0084474	0.6631134	0.00845	**	NA
SGK2	0.0084586	0.6631134	0.00846	**	NA
ADO	0.0085378	0.6631134	0.00854	**	NA
ZNF17	0.0085562	0.6631134	0.00856	**	NA
MFAP4	0.0085654	0.6631134	0.00857	**	NA
CD163	0.0085663	0.6631134	0.00857	**	NA
COL7A1	0.0085733	0.6631134	0.00857	**	NA
ARMC7	0.0085988	0.6631134	0.00860	**	NA
COL8A1	0.0086043	0.6631134	0.00860	**	NA
KHDC1L	0.0086562	0.6641352	0.00866	**	NA
PLCH2	0.0088368	0.6679256	0.00884	**	NA
OR13C3	0.0088398	0.6679256	0.00884	**	NA
C1orf141	0.0089498	0.6679256	0.00895	**	NA
ARHGEF17	0.0089894	0.6679256	0.00899	**	NA
COL9A2	0.0090078	0.6679256	0.00901	**	NA
H3F3A	0.0090755	0.6679256	0.00908	**	NA
ZC3H4	0.0091088	0.6679256	0.00911	**	NA
SUPT6H	0.0091374	0.6679256	0.00914	**	NA
CCNL1	0.0091597	0.6679256	0.00916	**	NA
MAML2	0.0091672	0.6679256	0.00917	**	NA
TMEM258	0.0091769	0.6679256	0.00918	**	NA
USP32	0.0092096	0.6679256	0.00921	**	NA
DNAJC8	0.0093058	0.6679256	0.00931	**	NA
C20orf26	0.0093466	0.6679256	0.00935	**	NA
KRTAP4-4	0.0093494	0.6679256	0.00935	**	NA
ACHE	0.0093636	0.6679256	0.00936	**	NA
LCTL	0.0093837	0.6679256	0.00938	**	NA
SLC25A4	0.0094344	0.6679256	0.00943	**	NA
LY6G6F	0.0095144	0.6679256	0.00951	**	NA
ZNF330	0.0095171	0.6679256	0.00952	**	NA
NECAB1	0.0095689	0.6679256	0.00957	**	NA
PPM1A	0.0095782	0.6679256	0.00958	**	NA
GMCL1	0.0096195	0.6679256	0.00962	**	NA
C16orf58	0.0096729	0.6679256	0.00967	**	NA
ZBTB44	0.0096904	0.6679256	0.00969	**	NA
INHBA	0.0097282	0.6679256	0.00973	**	NA
GLG1	0.0097693	0.6679256	0.00977	**	NA
RNF31	0.0098119	0.6679256	0.00981	**	NA
COPS3	0.0098996	0.6679256	0.00990	**	NA
NOL6	0.0099717	0.6679256	0.00997	**	NA
WDR77	0.0099778	0.6679256	0.00998	**	NA

wilcox_gene_allmut_delmis_plot <- ggplot(data = crispr_signif_allmut_delmis) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_gene_allmut_delmis_plot

5.2 Grouped by gene and lineage

5.2.1 Deleterious vs. Other

crispr_signif_allmut_del_lineage <- compare_means(Score ~ Mutation_Status_Deleterious, group.by = c("Hugo_Symbol", "group_general_lineage_name"), data = crispr_data, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_allmut_del_lineage <- adj_signif(crispr_signif_allmut_del_lineage)
crispr_signif_allmut_del_lineage <- crispr_signif_allmut_del_lineage[order(crispr_signif_allmut_del_lineage$p),]
saveRDS(crispr_signif_allmut_del_lineage, "./data_munging/rds/crispr_signif_allmut_deleterious_lineage.rds")

# write.table(crispr_signif_allmut_del_lineage, file = "~/Desktop/crispr_signif_allmut_deleterious_lineage.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_allmut_del_lineage <- readRDS("./data_munging/rds/crispr_signif_allmut_deleterious_lineage.rds")

knitr::kable(filter(crispr_signif_allmut_del_lineage, p < 0.01)[, c("Hugo_Symbol", "group_general_lineage_name", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing deleterious mutant vs other cell lines by lineage, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing deleterious mutant vs other cell lines by lineage, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	group_general_lineage_name	p	p.adj	p.format	p.signif	p.signif.adj
PTEN	central nervous system cancer	0.0006658	0.8331843	0.00067	***	NA
TP53	lung cancer	0.0006718	0.8331843	0.00067	***	NA
ZNF141	central nervous system cancer	0.0031757	0.8331843	0.00318	**	NA
DCAF8	lung cancer	0.0033009	0.8331843	0.00330	**	NA
PTEN	ovarian cancer	0.0048168	0.8331843	0.00482	**	NA
ARID1B	ovarian cancer	0.0054869	0.8331843	0.00549	**	NA
IFT122	lung cancer	0.0055037	0.8331843	0.00550	**	NA
SETD2	kidney cancer	0.0056647	0.8331843	0.00566	**	NA
KRT17	breast cancer	0.0063661	0.8331843	0.00637	**	NA
DVL2	uterine cancer	0.0067676	0.8331843	0.00677	**	NA
ARID1A	pancreatic cancer	0.0076726	0.8331843	0.00767	**	NA
MCPH1	lung cancer	0.0077467	0.8331843	0.00775	**	NA
COX4I1	lung cancer	0.0091372	0.8331843	0.00914	**	NA
ZNF343	lung cancer	0.0098486	0.8331843	0.00985	**	NA

wilcox_lineage_allmut_plot <- ggplot(data = crispr_signif_allmut_del_lineage) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_lineage_allmut_plot

5.2.2 Non-silent mutant vs. Other

crispr_signif_allmut_nonsilent_lineage <- compare_means(Score ~ Mutation_Status_Nonsilent, group.by = c("Hugo_Symbol", "group_general_lineage_name"), data = crispr_data, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_allmut_nonsilent_lineage <- adj_signif(crispr_signif_allmut_nonsilent_lineage)
crispr_signif_allmut_nonsilent_lineage <- crispr_signif_allmut_nonsilent_lineage[order(crispr_signif_allmut_nonsilent_lineage$p),]
saveRDS(crispr_signif_allmut_nonsilent_lineage, "./data_munging/rds/crispr_signif_allmut_nonsilent_lineage.rds")

# write.table(crispr_signif_allmut_nonsilent_lineage, file = "~/Desktop/crispr_signif_allmut_nonsilent_lineage.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_allmut_nonsilent_lineage <- readRDS("./data_munging/rds/crispr_signif_allmut_nonsilent_lineage.rds")

knitr::kable(filter(crispr_signif_allmut_nonsilent_lineage, p < 0.01)[, c("Hugo_Symbol", "group_general_lineage_name", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing non-silent mutant vs other cell lines by lineage, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing non-silent mutant vs other cell lines by lineage, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	group_general_lineage_name	p	p.adj	p.format	p.signif	p.signif.adj
KRAS	lung cancer	0.0000000	0.0000734	5.9e-10	****	****
TP53	lung cancer	0.0000047	0.2961085	4.7e-06	****	NA
TP53	central nervous system cancer	0.0000302	0.8628420	3.0e-05	****	NA
TP53	ovarian cancer	0.0001395	0.8628420	0.00014	***	NA
KRAS	ovarian cancer	0.0001488	0.8628420	0.00015	***	NA
NRAS	leukemia	0.0005316	0.8628420	0.00053	***	NA
TP53	leukemia	0.0005388	0.8628420	0.00054	***	NA
NRAS	skin cancer	0.0006117	0.8628420	0.00061	***	NA
TP53	skin cancer	0.0008277	0.8628420	0.00083	***	NA
PIK3CA	ovarian cancer	0.0008371	0.8628420	0.00084	***	NA
DZANK1	breast cancer	0.0009819	0.8628420	0.00098	***	NA
PIK3CA	breast cancer	0.0009842	0.8628420	0.00098	***	NA
KRAS	colorectal cancer	0.0010547	0.8628420	0.00105	**	NA
UNC45B	lung cancer	0.0011215	0.8628420	0.00112	**	NA
VHL	kidney cancer	0.0011846	0.8628420	0.00118	**	NA
KRT17	breast cancer	0.0012972	0.8628420	0.00130	**	NA
PIK3R1	central nervous system cancer	0.0013246	0.8628420	0.00132	**	NA
GOLGA3	uterine cancer	0.0013666	0.8628420	0.00137	**	NA
NRAS	multiple myeloma	0.0013756	0.8628420	0.00138	**	NA
GTF3C1	lung cancer	0.0013893	0.8628420	0.00139	**	NA
TICRR	uterine cancer	0.0014839	0.8628420	0.00148	**	NA
ARID1A	pancreatic cancer	0.0014920	0.8628420	0.00149	**	NA
TP53	kidney cancer	0.0016347	0.8628420	0.00163	**	NA
HYDIN	colorectal cancer	0.0017600	0.8628420	0.00176	**	NA
PTEN	ovarian cancer	0.0018079	0.8628420	0.00181	**	NA
HYOU1	colorectal cancer	0.0018107	0.8628420	0.00181	**	NA
USP34	breast cancer	0.0018820	0.8628420	0.00188	**	NA
MGA	uterine cancer	0.0019495	0.8628420	0.00195	**	NA
SVOPL	lung cancer	0.0019973	0.8628420	0.00200	**	NA
LILRB2	leukemia	0.0021670	0.8628420	0.00217	**	NA
PIK3R1	ovarian cancer	0.0021769	0.8628420	0.00218	**	NA
KMT2B	stomach cancer	0.0022800	0.8628420	0.00228	**	NA
TNRC6A	lung cancer	0.0023744	0.8628420	0.00237	**	NA
COX4I1	lung cancer	0.0023949	0.8628420	0.00239	**	NA
SNX29	uterine cancer	0.0026104	0.8628420	0.00261	**	NA
KIF3B	ovarian cancer	0.0026230	0.8628420	0.00262	**	NA
KMT2B	breast cancer	0.0026433	0.8628420	0.00264	**	NA
GSPT1	colorectal cancer	0.0028115	0.8628420	0.00281	**	NA
BRAF	ovarian cancer	0.0028709	0.8628420	0.00287	**	NA
AP1G2	breast cancer	0.0029835	0.8628420	0.00298	**	NA
ZNF264	colorectal cancer	0.0029879	0.8628420	0.00299	**	NA
ZNF141	central nervous system cancer	0.0031757	0.8628420	0.00318	**	NA
KMT2B	ovarian cancer	0.0032684	0.8628420	0.00327	**	NA
KIAA0586	colorectal cancer	0.0032838	0.8628420	0.00328	**	NA
ANK2	colorectal cancer	0.0033597	0.8628420	0.00336	**	NA
RPS19BP1	multiple myeloma	0.0034613	0.8628420	0.00346	**	NA
TGS1	uterine cancer	0.0035864	0.8628420	0.00359	**	NA
COL2A1	leukemia	0.0036054	0.8628420	0.00361	**	NA
SLIT3	leukemia	0.0036054	0.8628420	0.00361	**	NA
TP53	colorectal cancer	0.0036994	0.8628420	0.00370	**	NA
HTR7	lung cancer	0.0037248	0.8628420	0.00372	**	NA
PAPPA	uterine cancer	0.0037971	0.8628420	0.00380	**	NA
ZNF292	lung cancer	0.0038193	0.8628420	0.00382	**	NA
PTEN	central nervous system cancer	0.0038648	0.8628420	0.00386	**	NA
KRAS	stomach cancer	0.0040001	0.8628420	0.00400	**	NA
MTMR3	lung cancer	0.0041192	0.8628420	0.00412	**	NA
TSKS	uterine cancer	0.0042550	0.8628420	0.00425	**	NA
ARHGAP12	colorectal cancer	0.0042860	0.8628420	0.00429	**	NA
PAM	uterine cancer	0.0043488	0.8628420	0.00435	**	NA
PDE10A	uterine cancer	0.0043488	0.8628420	0.00435	**	NA
BRAF	skin cancer	0.0043710	0.8628420	0.00437	**	NA
ECT2L	central nervous system cancer	0.0044085	0.8628420	0.00441	**	NA
MAML2	uterine cancer	0.0044510	0.8628420	0.00445	**	NA
ARID1B	ovarian cancer	0.0046380	0.8628420	0.00464	**	NA
NCOR2	colorectal cancer	0.0046575	0.8628420	0.00466	**	NA
NLRP9	lung cancer	0.0046872	0.8628420	0.00469	**	NA
LRP4	uterine cancer	0.0046963	0.8628420	0.00470	**	NA
VAV3	lung cancer	0.0047769	0.8628420	0.00478	**	NA
NUP88	uterine cancer	0.0048888	0.8628420	0.00489	**	NA
LRRIQ1	central nervous system cancer	0.0049271	0.8628420	0.00493	**	NA
PTEN	uterine cancer	0.0050051	0.8628420	0.00501	**	NA
AXIN1	ovarian cancer	0.0050354	0.8628420	0.00504	**	NA
PIK3CA	colorectal cancer	0.0050602	0.8628420	0.00506	**	NA
TNK2	uterine cancer	0.0050864	0.8628420	0.00509	**	NA
DIP2C	kidney cancer	0.0052747	0.8628420	0.00527	**	NA
CTAGE15	lung cancer	0.0053375	0.8628420	0.00534	**	NA
LSP1	colorectal cancer	0.0053452	0.8628420	0.00535	**	NA
CORIN	colorectal cancer	0.0054756	0.8628420	0.00548	**	NA
SETD2	kidney cancer	0.0056647	0.8628420	0.00566	**	NA
FNDC7	colorectal cancer	0.0057059	0.8628420	0.00571	**	NA
SKOR1	uterine cancer	0.0057795	0.8628420	0.00578	**	NA
PARD3B	uterine cancer	0.0059302	0.8628420	0.00593	**	NA
FNIP1	ovarian cancer	0.0060557	0.8628420	0.00606	**	NA
AP2A2	breast cancer	0.0061570	0.8628420	0.00616	**	NA
ASXL1	colorectal cancer	0.0061648	0.8628420	0.00616	**	NA
CCT8L2	colorectal cancer	0.0061648	0.8628420	0.00616	**	NA
MTMR14	colorectal cancer	0.0061648	0.8628420	0.00616	**	NA
TTC32	uterine cancer	0.0062881	0.8628420	0.00629	**	NA
NR4A1	lung cancer	0.0064934	0.8628420	0.00649	**	NA
SLC22A17	lung cancer	0.0064934	0.8628420	0.00649	**	NA
FAM208B	colorectal cancer	0.0065065	0.8628420	0.00651	**	NA
ROCK1	colorectal cancer	0.0066106	0.8628420	0.00661	**	NA
ZNF521	colorectal cancer	0.0066975	0.8628420	0.00670	**	NA
RFWD3	lung cancer	0.0067488	0.8628420	0.00675	**	NA
TYRP1	lung cancer	0.0067488	0.8628420	0.00675	**	NA
ADRBK2	uterine cancer	0.0067676	0.8628420	0.00677	**	NA
DVL2	uterine cancer	0.0067676	0.8628420	0.00677	**	NA
EXOC8	uterine cancer	0.0067676	0.8628420	0.00677	**	NA
VPS51	pancreatic cancer	0.0067999	0.8628420	0.00680	**	NA
ITSN1	colorectal cancer	0.0069403	0.8628420	0.00694	**	NA
ZNF292	colorectal cancer	0.0069403	0.8628420	0.00694	**	NA
OR5M8	colorectal cancer	0.0070184	0.8628420	0.00702	**	NA
C10orf76	ovarian cancer	0.0070773	0.8628420	0.00708	**	NA
DDX11	lung cancer	0.0070952	0.8628420	0.00710	**	NA
KMT2C	multiple myeloma	0.0071541	0.8628420	0.00715	**	NA
MYH6	uterine cancer	0.0071786	0.8628420	0.00718	**	NA
SURF6	uterine cancer	0.0073058	0.8628420	0.00731	**	NA
GLP2R	lung cancer	0.0073425	0.8628420	0.00734	**	NA
C1orf86	leukemia	0.0073710	0.8628420	0.00737	**	NA
TEX10	ovarian cancer	0.0075601	0.8628420	0.00756	**	NA
ALPK3	ovarian cancer	0.0076300	0.8628420	0.00763	**	NA
MYOM3	lung cancer	0.0076435	0.8628420	0.00764	**	NA
ALPPL2	ovarian cancer	0.0077480	0.8628420	0.00775	**	NA
PNPLA5	colorectal cancer	0.0077740	0.8628420	0.00777	**	NA
PTPRN2	colorectal cancer	0.0078299	0.8628420	0.00783	**	NA
PTGFRN	lung cancer	0.0078691	0.8628420	0.00787	**	NA
PCDH10	uterine cancer	0.0078925	0.8628420	0.00789	**	NA
ANKRD23	colorectal cancer	0.0078965	0.8628420	0.00790	**	NA
RB1	central nervous system cancer	0.0079424	0.8628420	0.00794	**	NA
HERC1	skin cancer	0.0079501	0.8628420	0.00795	**	NA
RANBP2	colorectal cancer	0.0079744	0.8628420	0.00797	**	NA
SCFD1	colorectal cancer	0.0079828	0.8628420	0.00798	**	NA
C12orf4	uterine cancer	0.0080215	0.8628420	0.00802	**	NA
EGFLAM	lung cancer	0.0081906	0.8628420	0.00819	**	NA
FAM160B1	ovarian cancer	0.0082030	0.8628420	0.00820	**	NA
SPRED1	lung cancer	0.0084512	0.8628420	0.00845	**	NA
MROH1	pancreatic cancer	0.0084519	0.8628420	0.00845	**	NA
SBF2	lung cancer	0.0084541	0.8628420	0.00845	**	NA
EFCAB5	ovarian cancer	0.0084624	0.8628420	0.00846	**	NA
THSD7A	lung cancer	0.0085271	0.8628420	0.00853	**	NA
C6orf211	uterine cancer	0.0085754	0.8628420	0.00858	**	NA
CSNK1D	uterine cancer	0.0085754	0.8628420	0.00858	**	NA
FAM110A	uterine cancer	0.0085754	0.8628420	0.00858	**	NA
MICAL1	uterine cancer	0.0085754	0.8628420	0.00858	**	NA
MORF4L1	uterine cancer	0.0085754	0.8628420	0.00858	**	NA
RIOK2	uterine cancer	0.0085754	0.8628420	0.00858	**	NA
GAA	colorectal cancer	0.0085960	0.8628420	0.00860	**	NA
KIAA1107	colorectal cancer	0.0085960	0.8628420	0.00860	**	NA
ZNF536	skin cancer	0.0086987	0.8628420	0.00870	**	NA
RPS6KA2	uterine cancer	0.0087779	0.8628420	0.00878	**	NA
NF1	peripheral nervous system neoplasm	0.0088143	0.8628420	0.00881	**	NA
TPR	lung cancer	0.0088831	0.8628420	0.00888	**	NA
NFE2L2	esophageal cancer	0.0088890	0.8628420	0.00889	**	NA
TECRL	lung cancer	0.0089331	0.8628420	0.00893	**	NA
CLEC9A	liver cancer	0.0090085	0.8628420	0.00901	**	NA
SVEP1	skin cancer	0.0090238	0.8628420	0.00902	**	NA
DPYSL5	uterine cancer	0.0091517	0.8628420	0.00915	**	NA
FAM189A1	uterine cancer	0.0091517	0.8628420	0.00915	**	NA
HSPB2	uterine cancer	0.0091517	0.8628420	0.00915	**	NA
IRX6	uterine cancer	0.0091517	0.8628420	0.00915	**	NA
XKR9	uterine cancer	0.0091517	0.8628420	0.00915	**	NA
KIAA0922	lung cancer	0.0091532	0.8628420	0.00915	**	NA
STK17B	lung cancer	0.0092125	0.8628420	0.00921	**	NA
TTF1	lung cancer	0.0092125	0.8628420	0.00921	**	NA
SYNE1	lung cancer	0.0092324	0.8628420	0.00923	**	NA
TBC1D10B	uterine cancer	0.0092568	0.8628420	0.00926	**	NA
DNAJC8	uterine cancer	0.0092717	0.8628420	0.00927	**	NA
PKDCC	uterine cancer	0.0092717	0.8628420	0.00927	**	NA
TCF3	uterine cancer	0.0092717	0.8628420	0.00927	**	NA
ZNF207	uterine cancer	0.0093098	0.8628420	0.00931	**	NA
RASIP1	colorectal cancer	0.0093199	0.8628420	0.00932	**	NA
AP5B1	uterine cancer	0.0093215	0.8628420	0.00932	**	NA
RAD50	leukemia	0.0094090	0.8628420	0.00941	**	NA
DNAH5	colorectal cancer	0.0095928	0.8628420	0.00959	**	NA
TJP3	head and neck cancer	0.0096224	0.8628420	0.00962	**	NA
NRP2	colorectal cancer	0.0096226	0.8628420	0.00962	**	NA
INTS4	uterine cancer	0.0096407	0.8628420	0.00964	**	NA
TCHH	liver cancer	0.0096613	0.8628420	0.00966	**	NA
TTF1	leukemia	0.0097690	0.8628420	0.00977	**	NA
ZNF343	lung cancer	0.0098486	0.8628420	0.00985	**	NA
ZNF469	uterine cancer	0.0099581	0.8628420	0.00996	**	NA
IPO4	uterine cancer	0.0099688	0.8628420	0.00997	**	NA

wilcox_lineage_allmut_nonsilent_plot <- ggplot(data = crispr_signif_allmut_nonsilent_lineage) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_lineage_allmut_nonsilent_plot

5.2.3 Deleterious and missense mutant vs. Other

crispr_signif_allmut_delmis_lineage <- compare_means(Score ~ Mutation_Status_DeleteriousMissense, group.by = c("Hugo_Symbol", "group_general_lineage_name"), data = crispr_data, method = "wilcox.test", p.adjust.method = "BH")
crispr_signif_allmut_delmis_lineage <- adj_signif(crispr_signif_allmut_delmis_lineage)
crispr_signif_allmut_delmis_lineage <- crispr_signif_allmut_delmis_lineage[order(crispr_signif_allmut_delmis_lineage$p),]
saveRDS(crispr_signif_allmut_delmis_lineage, "./data_munging/rds/crispr_signif_allmut_deleteriousmissens_lineage.rds")

# write.table(crispr_signif_allmut_delmis_lineage, file = "~/Desktop/crispr_signif_allmut_deleteriousmissense_lineage.csv", quote = FALSE, sep = ",", row.names = FALSE)

crispr_signif_allmut_delmis_lineage <- readRDS("./data_munging/rds/crispr_signif_allmut_deleteriousmissens_lineage.rds")

knitr::kable(filter(crispr_signif_allmut_delmis_lineage, p < 0.01)[, c("Hugo_Symbol", "group_general_lineage_name", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "Wilcoxon test results comparing deleterious vs missense mutant and other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

Wilcoxon test results comparing deleterious vs missense mutant and other cell lines, p < 0.01 (BH-adjusted p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)

Hugo_Symbol	group_general_lineage_name	p	p.adj	p.format	p.signif	p.signif.adj
KRAS	lung cancer	0.0000000	0.0000729	5.9e-10	****	****
TP53	lung cancer	0.0000104	0.6484491	1.0e-05	****	NA
TP53	ovarian cancer	0.0001395	0.8627299	0.00014	***	NA
KRAS	ovarian cancer	0.0001488	0.8627299	0.00015	***	NA
TP53	central nervous system cancer	0.0004398	0.8627299	0.00044	***	NA
NRAS	leukemia	0.0005316	0.8627299	0.00053	***	NA
TP53	leukemia	0.0005388	0.8627299	0.00054	***	NA
NRAS	skin cancer	0.0006117	0.8627299	0.00061	***	NA
TP53	skin cancer	0.0008277	0.8627299	0.00083	***	NA
PIK3CA	ovarian cancer	0.0008371	0.8627299	0.00084	***	NA
DZANK1	breast cancer	0.0009819	0.8627299	0.00098	***	NA
PIK3CA	breast cancer	0.0009842	0.8627299	0.00098	***	NA
KRAS	colorectal cancer	0.0010547	0.8627299	0.00105	**	NA
UNC45B	lung cancer	0.0011215	0.8627299	0.00112	**	NA
KRT17	breast cancer	0.0012972	0.8627299	0.00130	**	NA
GOLGA3	uterine cancer	0.0013666	0.8627299	0.00137	**	NA
NRAS	multiple myeloma	0.0013756	0.8627299	0.00138	**	NA
GTF3C1	lung cancer	0.0013893	0.8627299	0.00139	**	NA
TICRR	uterine cancer	0.0014839	0.8627299	0.00148	**	NA
ARID1A	pancreatic cancer	0.0014920	0.8627299	0.00149	**	NA
HYOU1	colorectal cancer	0.0018107	0.8627299	0.00181	**	NA
USP34	breast cancer	0.0018820	0.8627299	0.00188	**	NA
MGA	uterine cancer	0.0019495	0.8627299	0.00195	**	NA
SVOPL	lung cancer	0.0019973	0.8627299	0.00200	**	NA
KMT2B	stomach cancer	0.0022800	0.8627299	0.00228	**	NA
ARID1B	ovarian cancer	0.0022924	0.8627299	0.00229	**	NA
TNRC6A	lung cancer	0.0023744	0.8627299	0.00237	**	NA
SNX29	uterine cancer	0.0026104	0.8627299	0.00261	**	NA
KIF3B	ovarian cancer	0.0026230	0.8627299	0.00262	**	NA
KMT2B	breast cancer	0.0026433	0.8627299	0.00264	**	NA
GSPT1	colorectal cancer	0.0028115	0.8627299	0.00281	**	NA
AP1G2	breast cancer	0.0029835	0.8627299	0.00298	**	NA
ZNF264	colorectal cancer	0.0029879	0.8627299	0.00299	**	NA
ZNF141	central nervous system cancer	0.0031757	0.8627299	0.00318	**	NA
KMT2B	ovarian cancer	0.0032684	0.8627299	0.00327	**	NA
KIAA0586	colorectal cancer	0.0032838	0.8627299	0.00328	**	NA
ANK2	colorectal cancer	0.0033597	0.8627299	0.00336	**	NA
RPS19BP1	multiple myeloma	0.0034613	0.8627299	0.00346	**	NA
TGS1	uterine cancer	0.0035864	0.8627299	0.00359	**	NA
COL2A1	leukemia	0.0036054	0.8627299	0.00361	**	NA
SLIT3	leukemia	0.0036054	0.8627299	0.00361	**	NA
TP53	colorectal cancer	0.0036994	0.8627299	0.00370	**	NA
HTR7	lung cancer	0.0037248	0.8627299	0.00372	**	NA
PAPPA	uterine cancer	0.0037971	0.8627299	0.00380	**	NA
ZNF292	lung cancer	0.0038193	0.8627299	0.00382	**	NA
PTEN	central nervous system cancer	0.0038648	0.8627299	0.00386	**	NA
PTEN	ovarian cancer	0.0039517	0.8627299	0.00395	**	NA
KRAS	stomach cancer	0.0040001	0.8627299	0.00400	**	NA
MTMR3	lung cancer	0.0041192	0.8627299	0.00412	**	NA
TSKS	uterine cancer	0.0042550	0.8627299	0.00425	**	NA
PTEN	uterine cancer	0.0042857	0.8627299	0.00429	**	NA
ARHGAP12	colorectal cancer	0.0042860	0.8627299	0.00429	**	NA
PAM	uterine cancer	0.0043488	0.8627299	0.00435	**	NA
PDE10A	uterine cancer	0.0043488	0.8627299	0.00435	**	NA
BRAF	skin cancer	0.0043710	0.8627299	0.00437	**	NA
ECT2L	central nervous system cancer	0.0044085	0.8627299	0.00441	**	NA
VHL	kidney cancer	0.0046189	0.8627299	0.00462	**	NA
NCOR2	colorectal cancer	0.0046575	0.8627299	0.00466	**	NA
NLRP9	lung cancer	0.0046872	0.8627299	0.00469	**	NA
LRP4	uterine cancer	0.0046963	0.8627299	0.00470	**	NA
VAV3	lung cancer	0.0047769	0.8627299	0.00478	**	NA
NUP88	uterine cancer	0.0048888	0.8627299	0.00489	**	NA
LRRIQ1	central nervous system cancer	0.0049271	0.8627299	0.00493	**	NA
AXIN1	ovarian cancer	0.0050354	0.8627299	0.00504	**	NA
TNK2	uterine cancer	0.0050864	0.8627299	0.00509	**	NA
DIP2C	kidney cancer	0.0052747	0.8627299	0.00527	**	NA
CTAGE15	lung cancer	0.0053375	0.8627299	0.00534	**	NA
LSP1	colorectal cancer	0.0053452	0.8627299	0.00535	**	NA
CORIN	colorectal cancer	0.0054756	0.8627299	0.00548	**	NA
SETD2	kidney cancer	0.0056647	0.8627299	0.00566	**	NA
FNDC7	colorectal cancer	0.0057059	0.8627299	0.00571	**	NA
SKOR1	uterine cancer	0.0057795	0.8627299	0.00578	**	NA
HYDIN	colorectal cancer	0.0057929	0.8627299	0.00579	**	NA
PARD3B	uterine cancer	0.0059302	0.8627299	0.00593	**	NA
FNIP1	ovarian cancer	0.0060557	0.8627299	0.00606	**	NA
AP2A2	breast cancer	0.0061570	0.8627299	0.00616	**	NA
ASXL1	colorectal cancer	0.0061648	0.8627299	0.00616	**	NA
CCT8L2	colorectal cancer	0.0061648	0.8627299	0.00616	**	NA
MTMR14	colorectal cancer	0.0061648	0.8627299	0.00616	**	NA
TTC32	uterine cancer	0.0062881	0.8627299	0.00629	**	NA
NR4A1	lung cancer	0.0064934	0.8627299	0.00649	**	NA
SLC22A17	lung cancer	0.0064934	0.8627299	0.00649	**	NA
FAM208B	colorectal cancer	0.0065065	0.8627299	0.00651	**	NA
ROCK1	colorectal cancer	0.0066106	0.8627299	0.00661	**	NA
ZNF521	colorectal cancer	0.0066975	0.8627299	0.00670	**	NA
RFWD3	lung cancer	0.0067488	0.8627299	0.00675	**	NA
TYRP1	lung cancer	0.0067488	0.8627299	0.00675	**	NA
ADRBK2	uterine cancer	0.0067676	0.8627299	0.00677	**	NA
DVL2	uterine cancer	0.0067676	0.8627299	0.00677	**	NA
EXOC8	uterine cancer	0.0067676	0.8627299	0.00677	**	NA
VPS51	pancreatic cancer	0.0067999	0.8627299	0.00680	**	NA
ITSN1	colorectal cancer	0.0069403	0.8627299	0.00694	**	NA
ZNF292	colorectal cancer	0.0069403	0.8627299	0.00694	**	NA
OR5M8	colorectal cancer	0.0070184	0.8627299	0.00702	**	NA
C10orf76	ovarian cancer	0.0070773	0.8627299	0.00708	**	NA
DDX11	lung cancer	0.0070952	0.8627299	0.00710	**	NA
KMT2C	multiple myeloma	0.0071541	0.8627299	0.00715	**	NA
MYH6	uterine cancer	0.0071786	0.8627299	0.00718	**	NA
SURF6	uterine cancer	0.0073058	0.8627299	0.00731	**	NA
PIK3CA	colorectal cancer	0.0073288	0.8627299	0.00733	**	NA
GLP2R	lung cancer	0.0073425	0.8627299	0.00734	**	NA
C1orf86	leukemia	0.0073710	0.8627299	0.00737	**	NA
TEX10	ovarian cancer	0.0075601	0.8627299	0.00756	**	NA
ALPK3	ovarian cancer	0.0076300	0.8627299	0.00763	**	NA
MYOM3	lung cancer	0.0076435	0.8627299	0.00764	**	NA
ALPPL2	ovarian cancer	0.0077480	0.8627299	0.00775	**	NA
TP53	kidney cancer	0.0077589	0.8627299	0.00776	**	NA
PNPLA5	colorectal cancer	0.0077740	0.8627299	0.00777	**	NA
PTPRN2	colorectal cancer	0.0078299	0.8627299	0.00783	**	NA
PTGFRN	lung cancer	0.0078691	0.8627299	0.00787	**	NA
PCDH10	uterine cancer	0.0078925	0.8627299	0.00789	**	NA
ANKRD23	colorectal cancer	0.0078965	0.8627299	0.00790	**	NA
RB1	central nervous system cancer	0.0079424	0.8627299	0.00794	**	NA
HERC1	skin cancer	0.0079501	0.8627299	0.00795	**	NA
SCFD1	colorectal cancer	0.0079828	0.8627299	0.00798	**	NA
C12orf4	uterine cancer	0.0080215	0.8627299	0.00802	**	NA
EGFLAM	lung cancer	0.0081906	0.8627299	0.00819	**	NA
SPRED1	lung cancer	0.0084512	0.8627299	0.00845	**	NA
MROH1	pancreatic cancer	0.0084519	0.8627299	0.00845	**	NA
SBF2	lung cancer	0.0084541	0.8627299	0.00845	**	NA
EFCAB5	ovarian cancer	0.0084624	0.8627299	0.00846	**	NA
C6orf211	uterine cancer	0.0085754	0.8627299	0.00858	**	NA
CSNK1D	uterine cancer	0.0085754	0.8627299	0.00858	**	NA
FAM110A	uterine cancer	0.0085754	0.8627299	0.00858	**	NA
MICAL1	uterine cancer	0.0085754	0.8627299	0.00858	**	NA
MORF4L1	uterine cancer	0.0085754	0.8627299	0.00858	**	NA
RIOK2	uterine cancer	0.0085754	0.8627299	0.00858	**	NA
GAA	colorectal cancer	0.0085960	0.8627299	0.00860	**	NA
KIAA1107	colorectal cancer	0.0085960	0.8627299	0.00860	**	NA
ZNF536	skin cancer	0.0086987	0.8627299	0.00870	**	NA
RPS6KA2	uterine cancer	0.0087779	0.8627299	0.00878	**	NA
TPR	lung cancer	0.0088831	0.8627299	0.00888	**	NA
SHANK1	central nervous system cancer	0.0088878	0.8627299	0.00889	**	NA
TECRL	lung cancer	0.0089331	0.8627299	0.00893	**	NA
CLEC9A	liver cancer	0.0090085	0.8627299	0.00901	**	NA
SVEP1	skin cancer	0.0090238	0.8627299	0.00902	**	NA
COX4I1	lung cancer	0.0091372	0.8627299	0.00914	**	NA
DPYSL5	uterine cancer	0.0091517	0.8627299	0.00915	**	NA
FAM189A1	uterine cancer	0.0091517	0.8627299	0.00915	**	NA
IRX6	uterine cancer	0.0091517	0.8627299	0.00915	**	NA
XKR9	uterine cancer	0.0091517	0.8627299	0.00915	**	NA
KIAA0922	lung cancer	0.0091532	0.8627299	0.00915	**	NA
TTF1	lung cancer	0.0092125	0.8627299	0.00921	**	NA
SYNE1	lung cancer	0.0092324	0.8627299	0.00923	**	NA
TBC1D10B	uterine cancer	0.0092568	0.8627299	0.00926	**	NA
DNAJC8	uterine cancer	0.0092717	0.8627299	0.00927	**	NA
PKDCC	uterine cancer	0.0092717	0.8627299	0.00927	**	NA
TCF3	uterine cancer	0.0092717	0.8627299	0.00927	**	NA
ZNF207	uterine cancer	0.0093098	0.8627299	0.00931	**	NA
RASIP1	colorectal cancer	0.0093199	0.8627299	0.00932	**	NA
AP5B1	uterine cancer	0.0093215	0.8627299	0.00932	**	NA
RAD50	leukemia	0.0094090	0.8627299	0.00941	**	NA
DNAH5	colorectal cancer	0.0095928	0.8627299	0.00959	**	NA
TJP3	head and neck cancer	0.0096224	0.8627299	0.00962	**	NA
NRP2	colorectal cancer	0.0096226	0.8627299	0.00962	**	NA
INTS4	uterine cancer	0.0096407	0.8627299	0.00964	**	NA
TCHH	liver cancer	0.0096613	0.8627299	0.00966	**	NA
TTF1	leukemia	0.0097690	0.8627299	0.00977	**	NA
ZNF343	lung cancer	0.0098486	0.8627299	0.00985	**	NA
LILRB2	leukemia	0.0098632	0.8627299	0.00986	**	NA
ZNF469	uterine cancer	0.0099581	0.8627299	0.00996	**	NA
IPO4	uterine cancer	0.0099688	0.8627299	0.00997	**	NA

wilcox_lineage_allmut_delmis_plot <- ggplot(data = crispr_signif_allmut_delmis_lineage) +
  geom_histogram(aes(x = p, fill = "chartreuse4"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  geom_histogram(aes(x = p.adj, fill = "darkslategray3"), breaks = seq(0, 1, by = 0.025), color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_fill_manual(name = "P-values", values = c("chartreuse4" = "chartreuse4", "darkslategray3" = "darkslategray3"), labels = c("Unadjusted", "BH-adjusted")) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position = c(0.1, 0.85)) +
  labs(x = "BH-adjusted p-values", y = "Frequency")
wilcox_lineage_allmut_delmis_plot

6 Paper outline

---

6.1 Figure 1C

Mutation status boxplots for genes identified in G2P.

genes_lvlA <- c("EGFR", "KRAS", "BRAF", "NRAS", "ERBB2", "MET", "ALK", "AKT1", "PDGFRA", "RET")
crispr_ptmuts_lvlA <- filter(crispr_data_ptmuts, Hugo_Symbol %in% genes_lvlA)
crispr_ptmuts_lvlA$Hugo_Symbol <- ordered(crispr_ptmuts_lvlA$Hugo_Symbol, levels = genes_lvlA)
crispr_ptmuts_lvlA_color <- as.character(crispr_ptmuts_lvlA$Color_DeleteriousMissense)
names(crispr_ptmuts_lvlA_color) <- crispr_ptmuts_lvlA$Mutation_Status_DeleteriousMissense

crispr_ptmuts_lvlA_plot <- ggplot(data = crispr_ptmuts_lvlA, aes(x = Hugo_Symbol, y = Score)) +
  geom_hline(yintercept = 0, lty = 2, color = "darkgray") +
  geom_violin(mapping = aes(fill = Mutation_Status_DeleteriousMissense), alpha = 0.7, position = position_dodge(0.85)) +
  geom_boxplot(mapping = aes(color = Mutation_Status_DeleteriousMissense), position = position_dodge(0.85), width = 0.1) +
  scale_fill_manual(values = crispr_ptmuts_lvlA_color) +
  scale_color_manual(values = c("black", "black")) +
  guides(color = FALSE) +
  theme(legend.direction = "horizontal", legend.justification = c(1, 0), legend.position = c(1, 0), legend.box.margin = margin(c(10, 10, 10, 10))) +
  labs(fill = "Mutation Status", y = "CERES Score", x = "Gene")
crispr_ptmuts_lvlA_plot

# ggsave("./plots_18Q3/manuscript/crispr_ptmuts_lvlA_plot.png", crispr_ptmuts_lvlA_plot, device = "png", width = 12, height = 5, units = "in")

crispr_ptmuts_lvlA_plot_faceted <- ggplot(data = crispr_ptmuts_lvlA, aes(x = Mutation_Status_DeleteriousMissense, y = Score)) +
  facet_wrap(~ Hugo_Symbol, ncol = length(unique(crispr_ptmuts_lvlA$Hugo_Symbol))) +
  geom_hline(yintercept = 0, lty = 2, color = "darkgray") +
  geom_violin(mapping = aes(fill = Mutation_Status_DeleteriousMissense), alpha = 0.7, position = position_dodge(0.85)) +
  geom_boxplot(mapping = aes(color = Mutation_Status_DeleteriousMissense), position = position_dodge(0.85), width = 0.1) +
  scale_fill_manual(values = crispr_ptmuts_lvlA_color) +
  scale_color_manual(values = c("black", "black")) +
  guides(color = FALSE) +
  theme(legend.direction = "horizontal", legend.justification = c(0.5, 0), legend.position = c(0.5, 0), legend.box.margin = margin(c(10, 10, 10, 10)), axis.ticks.x = element_blank(), axis.text.x = element_blank(), axis.title.x = element_blank()) +
  labs(fill = "Mutation Status", y = "CERES Score", x = "Mutation Status")
crispr_ptmuts_lvlA_plot_faceted

# ggsave("./plots_18Q3/manuscript/crispr_ptmuts_lvlA_plot_faceted.png", crispr_ptmuts_lvlA_plot_faceted, device = "png", width = 12, height = 5, units = "in")

6.2 Figure 1D

Match specific point mutations.

g2p_indications <- filter(read.delim("./data_munging/data_mutation_associations_appended.csv", sep = "\t", row.names = 1, header = TRUE), Evidence.Level == "A")
maf_g2p_indications <- filter(maf_raw, Genome_Change %in% g2p_indications$MutationName)
crispr_g2p_indications <- merge(maf_g2p_indications, crispr_data_ptmuts, by = c("Hugo_Symbol", "CCLE_Name", "Broad_ID"))
dup_g2p_indications <- filter(crispr_g2p_indications[, c("Hugo_Symbol", "CCLE_Name", "Broad_ID")] %>% group_by(Hugo_Symbol, CCLE_Name, Broad_ID) %>% tally(), n > 1)
crispr_g2p_indications <- merge(crispr_g2p_indications, dup_g2p_indications, by = c("Hugo_Symbol", "Broad_ID"), all.x = TRUE)
crispr_g2p_indications <- filter(crispr_g2p_indications, is.na(n))

crispr_g2p_indications_plot <- ggplot(crispr_g2p_indications, aes(x = Hugo_Symbol, y = Score)) +
  geom_hline(yintercept = 0, lty = 2, color = "darkgray") +
  geom_boxplot(alpha = 0.5, color = "lightgray", outlier.shape = NA) +
  geom_jitter(width = 0.3, mapping = aes(color = group_general_lineage_name), size = 1) +
  theme_light() +
  theme(legend.title = element_blank()) +
  labs(x = "Gene", y = "CERES Score")
crispr_g2p_indications_plot

# ggsave("./plots_18Q3/manuscript/crispr_g2p_indications_plot_test.png", crispr_g2p_indications_plot, width = 12, height = 5, units = "in")

7 Heatmaps

---

7.1 Data management

The mutation status portion of these heatmaps was made using deleterious and missense mutations as “mutant” and all others as “other.”

Make and save heatmap data matrices:

# Set up heatmap data
chm_scores <- t(crispr)
colnames(chm_scores) <- chm_scores[1, ]
chm_scores <- chm_scores[-1, ]
chm_rows <- rownames(chm_scores)
chm_cols <- colnames(chm_scores)
chm_scores <- apply(chm_scores, 2, as.double)
chm_scores <- apply(chm_scores, 2, function(x) (x - mean(x)) / var(x))
colnames(chm_scores) <- chm_cols
rownames(chm_scores) <- chm_rows
saveRDS(chm_scores, "./data_munging/rds/crispr_heatmap_scores.rds")

# Make full grid for genomic features
crispr_grid_ccls <- unique(crispr_data$Broad_ID)
crispr_grid_genes <- unique(crispr_data$Hugo_Symbol)
crispr_grid <- expand.grid("Broad_ID" = crispr_grid_ccls, "Hugo_Symbol" = crispr_grid_genes)

# Gene expression
ge_filt <- filter(ge_melt, Hugo_Symbol %in% unique(crispr_data$Hugo_Symbol))[, c("Hugo_Symbol", "Broad_ID", "RPKM")]
ge_filt$RPKM <- log2(ge_filt$RPKM + 0.0001)
chm_ge_grid <- merge(crispr_grid, ge_filt, by = c("Broad_ID", "Hugo_Symbol"), all.x = TRUE)
chm_ge <- reshape(chm_ge_grid, idvar = "Hugo_Symbol", timevar = "Broad_ID", direction = "wide")
chm_ge_rows <- chm_ge$Hugo_Symbol
chm_ge$Hugo_Symbol <- NULL
chm_ge_cols <- colnames(chm_ge) %>% gsub("RPKM.", "", .)
chm_ge <- apply(chm_ge, 2, as.double)
chm_ge <- apply(chm_ge, 2, function(x) (x - mean(x, na.rm = TRUE)) / var(x, na.rm = TRUE))
rownames(chm_ge) <- chm_ge_rows
colnames(chm_ge) <- chm_ge_cols
saveRDS(chm_ge, "./data_munging/rds/crispr_heatmap_ge.rds")

# Mutation status
chm_mut_grid <- merge(crispr_grid, maf_df[, c("Broad_ID", "Hugo_Symbol", "Mutation_Status")], by = c("Broad_ID", "Hugo_Symbol"), all.x = TRUE)
chm_mut_grid$Mutation_Status <- ifelse(is.na(chm_mut_grid$Mutation_Status), "Other", chm_mut_grid$Mutation_Status)
chm_mut_grid$Mutation_Status <- ifelse(chm_mut_grid$Mutation_Status == "Other", 0, 1)
chm_mut <- reshape(chm_mut_grid, idvar = "Hugo_Symbol", timevar = "Broad_ID", direction = "wide")
chm_mut_rows <- chm_mut$Hugo_Symbol
chm_mut$Hugo_Symbol <- NULL
chm_mut_cols <- colnames(chm_mut) %>% gsub("Mutation_Status.", "", .)
chm_mut <- matrix(as.numeric(unlist(chm_mut)), nrow = nrow(chm_mut))
rownames(chm_mut) <- chm_mut_rows
colnames(chm_mut) <- chm_mut_cols
saveRDS(chm_mut, "./data_munging/rds/crispr_heatmap_mut.rds")

# Copy number
cn_filt <- filter(cn_melt, Hugo_Symbol %in% unique(crispr_data$Hugo_Symbol))
chm_cn_grid <- merge(crispr_grid, cn_melt, by = c("Broad_ID", "Hugo_Symbol"), all.x = TRUE)
chm_cn <- reshape(chm_cn_grid, idvar = "Hugo_Symbol", timevar = "Broad_ID", direction = "wide")
chm_cn_rows <- chm_cn$Hugo_Symbol
chm_cn$Hugo_Symbol <- NULL
chm_cn_cols <- colnames(chm_cn) %>% gsub("Copy_Number.", "", .)
chm_cn <- apply(chm_cn, 2, as.double)
chm_cn <- apply(chm_cn, 2, function(x) (x - mean(x, na.rm = TRUE)) / var(x, na.rm = TRUE))
rownames(chm_cn) <- chm_cn_rows
colnames(chm_cn) <- chm_cn_cols
saveRDS(chm_cn, "./data_munging/rds/crispr_heatmap_cn.rds")

Load heatmap matrices:

chm_scores <- readRDS("./data_munging/rds/crispr_heatmap_scores.rds")
chm_ge <- readRDS("./data_munging/rds/crispr_heatmap_ge.rds")
chm_mut <- readRDS("./data_munging/rds/crispr_heatmap_mut.rds")
chm_cn <- readRDS("./data_munging/rds/crispr_heatmap_cn.rds")

# Metadata anotation dataframe
chm_annot <- merge(merge(data.frame("Broad_ID" = crispr$Broad_ID), crispr_meta[, c("Broad_ID", "cell_line_SSMD", "cas9_activity", "culture_type", "primary_tissue")], by = "Broad_ID", all.x = TRUE), ccl_info[, c("Broad_ID", "Primary.Disease", "Gender", "Source")], by = "Broad_ID", all.x = TRUE)
rownames(chm_annot) <- chm_annot$Broad_ID
chm_annot$Broad_ID <- NULL
colnames(chm_annot) <- c("Cell_Line_SSMD", "Cas9_Activity", "Culture_Type", "Primary_Tissue", "Primary_Disease", "Gender", "Source")
chm_annot$Cell_Line_SSMD <- as.numeric(chm_annot$Cell_Line_SSMD)
chm_annot$Cas9_Activity <- as.numeric(chm_annot$Cas9_Activity)

7.2 All genes, no omics

chm_annot_list <- HeatmapAnnotation(df = chm_annot, annotation_legend_param = list(
  Cell_Line_SSMD = list(title = "Cell Line SSMD", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
  Cas9_Activity = list(title = "Cas9 Activity", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
  Culture_Type = list(title = "Culture Type", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Culture Type", title_position = "topleft", grid_height = unit(0.3, "in")),
  Primary_Tissue = list(title = "Primary Tissue", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Primary_Tissue", title_position = "topleft", grid_height = unit(0.3, "in")),
  Primary_Disease = list(title = "Primary Disease", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Primary Disease", title_position = "topleft", grid_height = unit(0.3, "in")),
  Gender = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), grid_height = unit(0.3, "in")),
  Source = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Source", title_position = "topleft", grid_height = unit(0.3, "in"))))

chm_all_plot <- Heatmap(chm_scores, name = "CERES Score",
        bottom_annotation = chm_annot_list,
        bottom_annotation_height = unit(5, "in"),
        heatmap_legend_param = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
        row_title = "Genes", column_title = "Cancer Cell Lines",
        col = colorRamp2(c(min(chm_scores), 0, max(chm_scores)), c("purple4", "white", "seagreen4")),
        na_col = "black",
        row_title_gp = gpar(fontsize = 30, fontface = "bold"),
        row_names_gp = gpar(fontsize = 5),
        column_title_gp = gpar(fontsize = 30, fontface = "bold"),
        column_names_gp = gpar(fontsize = 5),
        row_dend_reorder = TRUE,
        column_dend_reorder = TRUE,
        clustering_distance_rows = "euclidean",
        clustering_distance_columns = "euclidean",
        clustering_method_rows = "complete",
        clustering_method_columns = "complete",
        column_dend_height = unit(2, "in"),
        row_dend_width = unit(4, "in"),
        width = 3)

pdf("./plots_18Q3/crispr_heatmap_euclidean_all.pdf", width = 50, height = 50, paper = "special")
draw(chm_all_plot, heatmap_legend_side = "bottom", annotation_legend_side = "bottom")
seekViewport("annotation_Cell_Line_SSMD")
grid.text("Cell Line SSMD", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Cas9_Activity")
grid.text("Cas9 Activity", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Culture_Type")
grid.text("Culture Type", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Primary_Tissue")
grid.text("Primary Tissue", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Primary_Disease")
grid.text("Primary Disease", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Gender")
grid.text("Gender", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Source")
grid.text("Source", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
dev.off()

png("./plots_18Q3/crispr_heatmap_euclidean_all.png", width = 50, height = 50, units = "in", res = 96)
draw(chm_all_plot, heatmap_legend_side = "bottom", annotation_legend_side = "bottom")
seekViewport("annotation_Cell_Line_SSMD")
grid.text("Cell Line SSMD", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Cas9_Activity")
grid.text("Cas9 Activity", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Culture_Type")
grid.text("Culture Type", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Primary_Tissue")
grid.text("Primary Tissue", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Primary_Disease")
grid.text("Primary Disease", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Gender")
grid.text("Gender", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Source")
grid.text("Source", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
dev.off()

7.3 CGC genes

Code for heatmap of CGC-filtered genes only

7.3.1 Euclidean distance

chm_scores_cgc <- subset(chm_scores, rownames(chm_scores) %in% cgc$Hugo_Symbol)
chm_ge_cgc <- subset(chm_ge, rownames(chm_ge) %in% cgc$Hugo_Symbol)
chm_mut_cgc <- subset(chm_mut, rownames(chm_mut) %in% cgc$Hugo_Symbol)
chm_cn_cgc <- subset(chm_cn, rownames(chm_cn) %in% cgc$Hugo_Symbol)

chm_annot_list <- HeatmapAnnotation(df = chm_annot, annotation_legend_param = list(
  Cell_Line_SSMD = list(title = "Cell Line SSMD", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
  Cas9_Activity = list(title = "Cas9 Activity", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
  Culture_Type = list(title = "Culture Type", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Culture Type", title_position = "topleft", grid_height = unit(0.3, "in")),
  Primary_Tissue = list(title = "Primary Tissue", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Primary_Tissue", title_position = "topleft", grid_height = unit(0.3, "in")),
  Primary_Disease = list(title = "Primary Disease", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Primary Disease", title_position = "topleft", grid_height = unit(0.3, "in")),
  Gender = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), grid_height = unit(0.3, "in")),
  Source = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Source", title_position = "topleft", grid_height = unit(0.3, "in"))))

chm_plot_cgc <- Heatmap(chm_scores_cgc, name = "CERES Score",
        bottom_annotation = chm_annot_list,
        bottom_annotation_height = unit(5, "in"),
        heatmap_legend_param = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
        row_title = "Genes", column_title = "Cancer Cell Lines",
        col = colorRamp2(c(min(chm_scores_cgc), 0, max(chm_scores_cgc)), c("purple4", "white", "seagreen4")),
        na_col = "black",
        row_title_gp = gpar(fontsize = 30, fontface = "bold"),
        row_names_gp = gpar(fontsize = 5),
        column_title_gp = gpar(fontsize = 30, fontface = "bold"),
        column_names_gp = gpar(fontsize = 5),
        row_dend_reorder = TRUE,
        column_dend_reorder = TRUE,
        clustering_distance_rows = "euclidean",
        clustering_distance_columns = "euclidean",
        clustering_method_rows = "complete",
        clustering_method_columns = "complete",
        column_dend_height = unit(2, "in"),
        row_dend_width = unit(4, "in"),
        width = 3)

chm_plot_cgc_cols <- colnames(chm_scores_cgc)[unlist(column_order(chm_plot_cgc))]
chm_plot_cgc_rows <- rownames(chm_scores_cgc)[unlist(row_order(chm_plot_cgc))]

chm_ge_plot_cgc <- Heatmap(chm_ge_cgc, name = "Gene Expression",
        col = colorRamp2(c(min(chm_ge_cgc[!is.na(chm_ge_cgc)]), 0, max(chm_ge_cgc[!is.na(chm_ge_cgc)])), c("dodgerblue4", "white", "firebrick4")),
        heatmap_legend_param = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
        na_col = "black",
        cluster_rows = FALSE, cluster_columns = FALSE,
        row_names_gp = gpar(fontsize = 5), show_column_names = FALSE,
        column_title = "Gene Expression",
        column_title_gp = gpar(fontsize = 30, fontface = "bold"),
        column_order = chm_plot_cgc_cols,
        row_order = chm_plot_cgc_rows,
        width = 1)
chm_cn_plot_cgc <- Heatmap(chm_cn_cgc, name = "Copy Number",
        col = colorRamp2(c(min(chm_cn_cgc[!is.na(chm_cn_cgc)]), 0, max(chm_cn_cgc[!is.na(chm_cn_cgc)])), c("white", "thistle2", "mediumorchid4")),
        heatmap_legend_param = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
        na_col = "black",
        cluster_rows = FALSE, cluster_columns = FALSE,
        row_names_gp = gpar(fontsize = 5), show_column_names = FALSE,
        column_title = "Copy Number",
        column_title_gp = gpar(fontsize = 30, fontface = "bold"),
        column_order = chm_plot_cgc_cols,
        row_order = chm_plot_cgc_rows,
        width = 1)
chm_mut_plot_cgc <- Heatmap(chm_mut_cgc, name = "Mutation Status",
        na_col = "black",
        heatmap_legend_param = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), at = c(0, 1), labels = c("Other", "Mutant"), title_position = "topcenter", grid_height = unit(0.3, "in")),
        col = c("cyan3", "darkorchid"),
        cluster_rows = FALSE, cluster_columns = FALSE,
        row_names_gp = gpar(fontsize = 5), show_column_names = FALSE,
        column_title = "Mutation Status",
        column_title_gp = gpar(fontsize = 30, fontface = "bold"),
        column_order = chm_plot_cgc_cols,
        row_order = chm_plot_cgc_rows,
        width = 1)

chm_all_plot_cgc <- chm_plot_cgc + chm_ge_plot_cgc + chm_cn_plot_cgc + chm_mut_plot_cgc

pdf("./plots_18Q3/crispr_heatmap_euclidean_all_cgc.pdf", width = 50, height = 50, paper = "special")
draw(chm_all_plot_cgc, heatmap_legend_side = "bottom", annotation_legend_side = "bottom")
seekViewport("annotation_Cell_Line_SSMD")
grid.text("Cell Line SSMD", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Cas9_Activity")
grid.text("Cas9 Activity", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Culture_Type")
grid.text("Culture Type", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Primary_Tissue")
grid.text("Primary Tissue", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Primary_Disease")
grid.text("Primary Disease", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Gender")
grid.text("Gender", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Source")
grid.text("Source", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
dev.off()

png("./plots_18Q3/crispr_heatmap_euclidean_all_cgc.png", width = 50, height = 50, units = "in", res = 96)
draw(chm_all_plot_cgc, heatmap_legend_side = "bottom", annotation_legend_side = "bottom")
seekViewport("annotation_Cell_Line_SSMD")
grid.text("Cell Line SSMD", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Cas9_Activity")
grid.text("Cas9 Activity", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Culture_Type")
grid.text("Culture Type", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Primary_Tissue")
grid.text("Primary Tissue", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Primary_Disease")
grid.text("Primary Disease", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Gender")
grid.text("Gender", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Source")
grid.text("Source", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
dev.off()

7.3.2 Pearson correlation

chm_scores_cgc <- subset(chm_scores, rownames(chm_scores) %in% cgc$Hugo_Symbol)
chm_ge_cgc <- subset(chm_ge, rownames(chm_ge) %in% cgc$Hugo_Symbol)
chm_mut_cgc <- subset(chm_mut, rownames(chm_mut) %in% cgc$Hugo_Symbol)
chm_cn_cgc <- subset(chm_cn, rownames(chm_cn) %in% cgc$Hugo_Symbol)

chm_annot_list <- HeatmapAnnotation(df = chm_annot, annotation_legend_param = list(
  Cell_Line_SSMD = list(title = "Cell Line SSMD", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
  Cas9_Activity = list(title = "Cas9 Activity", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
  Culture_Type = list(title = "Culture Type", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Culture Type", title_position = "topleft", grid_height = unit(0.3, "in")),
  Primary_Tissue = list(title = "Primary Tissue", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Primary_Tissue", title_position = "topleft", grid_height = unit(0.3, "in")),
  Primary_Disease = list(title = "Primary Disease", title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Primary Disease", title_position = "topleft", grid_height = unit(0.3, "in")),
  Gender = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), grid_height = unit(0.3, "in")),
  Source = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), nrow = 8, title = "Source", title_position = "topleft", grid_height = unit(0.3, "in"))))

chm_plot_cgc <- Heatmap(chm_scores_cgc, name = "CERES Score",
        bottom_annotation = chm_annot_list,
        bottom_annotation_height = unit(5, "in"),
        heatmap_legend_param = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
        row_title = "Genes", column_title = "Cancer Cell Lines",
        col = colorRamp2(c(min(chm_scores_cgc), 0, max(chm_scores_cgc)), c("purple4", "white", "seagreen4")),
        na_col = "black",
        row_title_gp = gpar(fontsize = 30, fontface = "bold"),
        row_names_gp = gpar(fontsize = 5),
        column_title_gp = gpar(fontsize = 30, fontface = "bold"),
        column_names_gp = gpar(fontsize = 5),
        row_dend_reorder = TRUE,
        column_dend_reorder = TRUE,
        clustering_distance_rows = "pearson",
        clustering_distance_columns = "pearson",
        clustering_method_rows = "complete",
        clustering_method_columns = "complete",
        column_dend_height = unit(2, "in"),
        row_dend_width = unit(4, "in"),
        width = 3)

chm_plot_cgc_cols <- colnames(chm_scores_cgc)[unlist(column_order(chm_plot_cgc))]
chm_plot_cgc_rows <- rownames(chm_scores_cgc)[unlist(row_order(chm_plot_cgc))]

chm_ge_plot_cgc <- Heatmap(chm_ge_cgc, name = "Gene Expression",
        col = colorRamp2(c(min(chm_ge_cgc[!is.na(chm_ge_cgc)]), 0, max(chm_ge_cgc[!is.na(chm_ge_cgc)])), c("dodgerblue4", "white", "firebrick4")),
        heatmap_legend_param = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
        na_col = "black",
        cluster_rows = FALSE, cluster_columns = FALSE,
        row_names_gp = gpar(fontsize = 5), show_column_names = FALSE,
        column_title = "Gene Expression",
        column_title_gp = gpar(fontsize = 30, fontface = "bold"),
        column_order = chm_plot_cgc_cols,
        row_order = chm_plot_cgc_rows,
        width = 1)
chm_cn_plot_cgc <- Heatmap(chm_cn_cgc, name = "Copy Number",
        col = colorRamp2(c(min(chm_cn_cgc[!is.na(chm_cn_cgc)]), 0, max(chm_cn_cgc[!is.na(chm_cn_cgc)])), c("white", "thistle2", "mediumorchid4")),
        heatmap_legend_param = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), title_position = "topcenter", legend_height = unit(2, "in")),
        na_col = "black",
        cluster_rows = FALSE, cluster_columns = FALSE,
        row_names_gp = gpar(fontsize = 5), show_column_names = FALSE,
        column_title = "Copy Number",
        column_title_gp = gpar(fontsize = 30, fontface = "bold"),
        column_order = chm_plot_cgc_cols,
        row_order = chm_plot_cgc_rows,
        width = 1)
chm_mut_plot_cgc <- Heatmap(chm_mut_cgc, name = "Mutation Status",
        na_col = "black",
        heatmap_legend_param = list(title_gp = gpar(fontsize = 20), labels_gp = gpar(fontsize = 15), at = c(0, 1), labels = c("Other", "Mutant"), title_position = "topcenter", grid_height = unit(0.3, "in")),
        col = c("cyan3", "darkorchid"),
        cluster_rows = FALSE, cluster_columns = FALSE,
        row_names_gp = gpar(fontsize = 5), show_column_names = FALSE,
        column_title = "Mutation Status",
        column_title_gp = gpar(fontsize = 30, fontface = "bold"),
        column_order = chm_plot_cgc_cols,
        row_order = chm_plot_cgc_rows,
        width = 1)

chm_all_plot_cgc <- chm_plot_cgc + chm_ge_plot_cgc + chm_cn_plot_cgc + chm_mut_plot_cgc

pdf("./plots_18Q3/crispr_heatmap_pearson_all_cgc.pdf", width = 50, height = 50, paper = "special")
draw(chm_all_plot_cgc, heatmap_legend_side = "bottom", annotation_legend_side = "bottom")
seekViewport("annotation_Cell_Line_SSMD")
grid.text("Cell Line SSMD", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Cas9_Activity")
grid.text("Cas9 Activity", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Culture_Type")
grid.text("Culture Type", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Primary_Tissue")
grid.text("Primary Tissue", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Primary_Disease")
grid.text("Primary Disease", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Gender")
grid.text("Gender", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
seekViewport("annotation_Source")
grid.text("Source", unit(1, "npc") + unit(1, "mm"), 0.5, gp = gpar(fontsize = 15), default.units = "npc", just = "left")
dev.off()

8 Per-gene plots

---

8.1 Grouped plots

Plot code:

crispr_data_cgc <- filter(crispr_data, Hugo_Symbol %in% cgc$Hugo_Symbol)
crispr_all_genes <- unique(crispr_data_cgc$Hugo_Symbol)
crispr_all_groups <- lapply(crispr_all_genes, makeCRISPRgrob)
crispr_all_groups_paths <- paste0(crispr_all_genes, "_crispr_grouped.png")
pwalk(list(crispr_all_groups_paths, crispr_all_groups), ggsave, path = "./plots_18Q3/crispr_grouped_plots_cgc", dpi = 300, width = 12, height = 12, units = "in")

Data management:

crispr_all_bygene <- paste0(list.files("./plots_18Q3/crispr_grouped_plots_cgc", full.names = TRUE))
names(crispr_all_bygene) <- str_replace_all(crispr_all_bygene, c("_crispr_grouped.png" = "", "./plots_18Q3/crispr_grouped_plots_cgc/" = ""))
crispr_bygene_order <- c(intersect(crispr_signif$Hugo_Symbol, names(crispr_all_bygene)), setdiff(names(crispr_all_bygene), crispr_signif$Hugo_Symbol))
crispr_all_bygene <- crispr_all_bygene[match(crispr_bygene_order, names(crispr_all_bygene))]
bsselect(crispr_all_bygene, type = "img", selected = "KRAS", live_search = TRUE, show_tick = TRUE, height = 300, frame_height = 275)

8.2 Sorted lineage plots

Plot code:

crispr_data_cgc <- filter(crispr_data, Hugo_Symbol %in% cgc$Hugo_Symbol)
crispr_all_genes <- unique(crispr_data_cgc$Hugo_Symbol)
crispr_all_lins <- lapply(crispr_all_genes, makeCRISPRlinplot)
crispr_all_lins_paths <- paste0(crispr_all_genes, "_crispr_lineage.png")
pwalk(list(crispr_all_lins_paths, crispr_all_lins), ggsave, path = "./plots_18Q3/crispr_lineage_plots_cgc", dpi = 300, width = 12, height = 12, units = "in")

Data management:

crispr_all_bygene <- paste0(list.files("./plots_18Q3/crispr_lineage_plots_cgc", full.names = TRUE))
names(crispr_all_bygene) <- str_replace_all(crispr_all_bygene, c("_crispr_lineage.png" = "", "./plots_18Q3/crispr_lineage_plots_cgc/" = ""))
crispr_bygene_order <- c(intersect(crispr_signif$Hugo_Symbol, names(crispr_all_bygene)), setdiff(names(crispr_all_bygene), crispr_signif$Hugo_Symbol))
crispr_all_bygene <- crispr_all_bygene[match(crispr_bygene_order, names(crispr_all_bygene))]
bsselect(crispr_all_bygene, type = "img", selected = "KRAS", live_search = TRUE, show_tick = TRUE, height = 300, frame_height = 275)

8.3 Sorted tissue plots

Plot code:

crispr_data_cgc <- filter(crispr_data, Hugo_Symbol %in% cgc$Hugo_Symbol)
crispr_all_genes <- unique(crispr_data_cgc$Hugo_Symbol)
crispr_all_lins <- lapply(crispr_all_genes, makeCRISPRtissueplot)
crispr_all_lins_paths <- paste0(crispr_all_genes, "_crispr_tissue.png")
pwalk(list(crispr_all_lins_paths, crispr_all_lins), ggsave, path = "./plots_18Q3/crispr_tissue_plots_cgc", dpi = 300, width = 12, height = 12, units = "in")

Data management:

crispr_all_bygene <- paste0(list.files("./plots_18Q3/crispr_tissue_plots_cgc", full.names = TRUE))
names(crispr_all_bygene) <- str_replace_all(crispr_all_bygene, c("_crispr_tissue.png" = "", "./plots_18Q3/crispr_tissue_plots_cgc/" = ""))
crispr_bygene_order <- c(intersect(crispr_signif$Hugo_Symbol, names(crispr_all_bygene)), setdiff(names(crispr_all_bygene), crispr_signif$Hugo_Symbol))
crispr_all_bygene <- crispr_all_bygene[match(crispr_bygene_order, names(crispr_all_bygene))]
bsselect(crispr_all_bygene, type = "img", selected = "KRAS", live_search = TRUE, show_tick = TRUE, height = 300, frame_height = 275)

9 Report #2

---

9.1 Metadata

tissue_summ <- crispr_meta %>% group_by(primary_tissue) %>% tally()
disease_summ <- ccl_info %>% group_by(Primary.Disease) %>% tally()

ggplot(data = tissue_summ) + 
  aes(x = 0, y = n, fill = primary_tissue, label = primary_tissue) +
  geom_histogram(color = "black", stat = "identity") +
  geom_text(position = position_stack(vjust = 0.5)) +
  scale_y_continuous(breaks = seq(0, 500, by = 25), labels = seq(0, 500, by = 25)) +
  coord_cartesian(ylim = c(0, 500)) +
  theme(legend.position = "none", axis.text.x = element_blank(), axis.ticks.x = element_blank(), axis.title.x = element_blank()) +
  labs(y = "Count")

9.2 Scores

Distribution of scores across cell lines and primary tissues. Each data point represents a single cell line.

ceres_summ <- crispr_data %>% group_by(primary_tissue) %>% summarize(Max = max(Score),
                                                                     Min = min(Score))
score_summ_plot <- ggplot(data = crispr_data, aes(x = primary_tissue, color = primary_tissue)) +
  geom_boxplot(mapping = aes(y = Score), outlier.shape = NA) +
  geom_point(data = ceres_summ, mapping = aes(x = primary_tissue, y = Min)) +
  geom_point(data = ceres_summ, mapping = aes(x = primary_tissue, y = Max)) +
  scale_y_continuous(breaks = seq(-4, 6, by = 1), labels = seq(-4, 6, by = 1)) +
  theme(axis.text.x = element_text(angle = 30, hjust = 1), legend.position = "none") +
  labs(x = "Primary Tissue", y = "CERES Score")
score_summ_plot

# ggsave(filename = "./plots_18Q3/crispr/ceres_score_summ_plot.pdf", plot = score_summ_plot, width = 12, height = 4, device = "pdf")

9.3 Mutations

maf_df_filt <- filter(maf_df, Hugo_Symbol %in% unique(crispr_data$Hugo_Symbol))
# maf_summ_filt <- maf_df_filt %>% group_by(Mutation_Status) %>% tally()
# maf_summ_filt$Percent <- format(round(maf_summ_filt$n / sum(maf_summ_filt$n) * 100, 4), nsmall = 2)
# maf_summ_filt$Percent <- as.numeric(as.character(maf_summ_filt$Percent))

Distribution of mutations across cell lines and primary tissues. Each data point represents a single cell line.

maf_ccl_annot <- merge(maf_df %>% group_by(Broad_ID) %>% tally(), crispr_meta, by = "Broad_ID", all.y = TRUE)

maf_ccl_annot_plot <- ggplot(data = maf_ccl_annot, aes(x = primary_tissue, y = n, color = primary_tissue)) +
  geom_boxplot(outlier.shape = NA, fill = NA) +
  geom_jitter(alpha = 0.7, size = 1, position = position_jitter(w = 0.25)) +
  scale_y_continuous(breaks = seq(0, 9000, by = 1000), labels = seq(0, 9000, by = 1000)) +
  theme(axis.ticks.x = element_blank(), axis.title.x = element_blank(), axis.text.x = element_blank(), legend.position = "none") +
  labs(x = "Primary Tissue", y = "Number of Mutations")
maf_ccl_annot_plot

# ggsave(filename = "./plots_18Q3/crispr/maf_ccl_annot_plot.pdf", plot = maf_ccl_annot_plot, width = 12, height = 4, device = "pdf")

# ggsave(filename = "./plots_18Q3/crispr/score_mut_summ.pdf", plot = grid.draw(rbind(ggplotGrob(maf_ccl_annot_plot), ggplotGrob(score_summ_plot), size = "first")), width = 12, height = 8, device = "pdf")

maf_gene_annot <- maf_df_filt %>% group_by(Hugo_Symbol) %>% tally()

ggplot(data = maf_gene_annot, aes(x = n)) +
  geom_histogram(breaks = seq(0, 600, by = 20), fill = "darkslategray3", color = "black", alpha = 0.7) +
  coord_cartesian(ylim = c(0, 13000)) +
  scale_y_continuous(breaks = seq(0, 13500, by = 500), labels = formatC(seq(0, 13500, by = 500), format = "d")) +
  scale_x_continuous(breaks = seq(0, 600, by = 20), labels = seq(0, 600, by = 20)) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  stat_bin(breaks = seq(0, 600, by = 20), geom = "text", colour = "black", size = 2.5, aes(label = ..count..), vjust = -0.2, angle = 45, hjust = -0.1) +
  labs(x = "Number of Mutations", y = "Frequency", title = paste0("Distribution of mutational load for ", length(unique(maf_gene_annot$Hugo_Symbol)), " genes in the CCLE MAF file across all ", length(unique(crispr_ccl$Broad_ID)), " cell lines in the CRISPR screen"))

9.4 Dependency probabilities

drop_prob_100 <- ggplot(data = crispr_data, aes(x = Dep_Prob)) +
  geom_histogram(breaks = seq(0, 1, by = 0.05), fill = "darkslategray3", color = "black", alpha = 0.7) +
  scale_x_continuous(breaks = seq(0, 1, by = 0.05), labels = seq(0, 1, by = 0.05)) +
  scale_y_continuous(breaks = seq(0, 5500000, by = 500000), labels = formatC(seq(0, 5500000, by = 500000), format = "d")) +
  stat_bin(breaks = seq(0, 1, by = 0.05), geom = "text", colour = "black", size = 3.5, aes(label = ..count..), vjust = -1) +
  labs(title = "Distribution of all dependency probabilities", x = "Probability of Real Dependency", y = "Frequency")

dep_prob_5 <- ggplot(data = filter(crispr_data, Dep_Prob >= 0.95), aes(x = Dep_Prob)) +
  geom_histogram(mapping = aes(fill = primary_tissue), breaks = seq(0.95, 1, by = 0.005), color = "black") +
  scale_y_continuous(breaks = seq(0, 60000, by = 10000), labels = formatC(seq(0, 60000, by = 10000), format = "d")) +
  theme(legend.position = "bottom") +
  guides(fill = guide_legend(nrow = 4, byrow = FALSE)) +
  stat_bin(breaks = seq(0.95, 1, by = 0.005), geom = "text", color = "black", size = 3.5, aes(label = ..count..), vjust = -1) +
  labs(title = "Distribution of all dependency probabilities > 0.95", x = "Probability of Real Dependency", y = "Frequency", fill = "Primary Tissue")

9.5 Per-gene plots

sig_genes <- c("KRAS", "TP53", "NRAS", "BRAF", "PIK3CA", "PTEN", "CTNNB1")
crispr_sig_genes <- filter(crispr_data, Hugo_Symbol %in% sig_genes)
crispr_sig_genes$Hugo_Symbol <- factor(crispr_sig_genes$Hugo_Symbol, levels = c("KRAS", "TP53", "NRAS", "BRAF", "PIK3CA", "PTEN", "CTNNB1"))

crispr_color <- as.character(crispr_sig_genes$Color)
names(crispr_color) <- crispr_sig_genes$Mutation_Status

# Mutation status
plot_mut <- ggplot(data = crispr_sig_genes, aes(x = Mutation_Status, y = Score, color = Mutation_Status)) +
  geom_boxplot(outlier.shape = NA) +
  geom_jitter(alpha = 0.3, size = 0.7, position = position_jitter(w = 0.05)) +
  facet_wrap(~ Hugo_Symbol, nrow = 7, scales = "free_y") +
  scale_color_manual(values = crispr_color) +
  geom_hline(yintercept = 0, linetype = 2, lwd = 0.3) +
  theme_light() +
  theme(legend.position = "none") +
  labs(x = "Mutation Status", y = "CERES Score",
       title = "Mutation Status")
# plot_mut

# Copy number
plot_cn <- ggplot(data = crispr_sig_genes, aes(x = Copy_Number, y = Score, color = Mutation_Status)) +
  geom_point(size = 0.5, alpha = 0.5) +
  geom_smooth(method = "lm", size = 0.5) +
  scale_color_manual(values = crispr_color) +
  facet_wrap(~ Hugo_Symbol, nrow = 7, scales = "free") +
  stat_cor(method = "pearson", show.legend = FALSE, label.x.npc = "right", label.y.npc = "top") +
  theme_light() +
  theme(legend.position = "none", axis.title.y = element_blank()) +
  labs(y = "CERES Score", color = "Mutation Status",
       x = "Theoretical Copy number", title = "Copy Number")
# plot_cn

# Gene expression
plot_ge <- ggplot(data = crispr_sig_genes, aes(x = RPKM_log2, y = Score, color = Mutation_Status)) +
  geom_point(size = 0.5, alpha = 0.5) +
  geom_smooth(method = "lm", size = 0.5) +
  facet_wrap(~ Hugo_Symbol, nrow = 7, scales = "free_y") +
  scale_color_manual(values = crispr_color) +
  stat_cor(method = "pearson", show.legend = FALSE, label.x.npc = "left", label.y.npc = "top") +
  theme_light() +
  theme(legend.position = "none", axis.title.y = element_blank()) +
  labs(y = "CERES Score", color = "Mutation Status",
       x = "Gene Expression [log2(RPKM)]",
       title = "Gene Expression")
# plot_ge

# ggsave(filename = "./plots_18Q3/crispr/omics_sig_genes.pdf", plot = grid.draw(cbind(ggplotGrob(plot_mut), ggplotGrob(plot_ge), ggplotGrob(plot_cn), size = "last")), width = 15, height = 18, device = "pdf")

10 shRNA

---

10.1 Data and annotations

DepMap cell line metadata:

# From figshare
shrna_meta <- read.delim("./data_munging/sample_info_18Q3_shrna.csv", sep = ",", header = TRUE, na.strings = c("", NA))
colnames(shrna_meta)[1] <- "CCLE_Name"

The Achilles shRNA DEMETER score data was pulled from the CTD² Data Portal (Tsherniak et al 2017).

shrna <- read.table("./data_munging/D2_combined_gene_dep_scores.csv.gz", sep = ",", header = TRUE, check.names = FALSE)
colnames(shrna)[1] <- "Hugo_Symbol"
# Remove Entrez gene IDs from gene names
shrna$Hugo_Symbol <- gsub(" .*", "", shrna$Hugo_Symbol)

# Melt shRNA dataset for merging
shrna_melt <- melt(shrna , id.vars = "Hugo_Symbol", measure.vars = colnames(shrna)[2:ncol(shrna)], variable.name = "CCLE_Name", value.name = "Score")
shrna_melt <- drop_na(shrna_melt)

Merge annotation data:

# Merge cell line metadata
shrna_melt <- merge(shrna_melt, ccl_info, by = "CCLE_Name", all.x = TRUE)
shrna_melt <- merge(shrna_melt, shrna_meta, by = "CCLE_Name", all.x = TRUE)

# Merge mutation annotations
shrna_muts <- merge(shrna_melt, maf_df, by = c("Hugo_Symbol", "CCLE_Name", "Broad_ID"), all.x = TRUE)
shrna_muts <- shrna_muts %>% mutate(Mutation_Status = if_else(is.na(Mutation_Status), "Other", Mutation_Status))
shrna_muts$Hugo_Symbol <- factor(shrna_muts$Hugo_Symbol)

# Summarize number of mutant and Other cell lines
shrna_muts_summ <- shrna_muts %>% group_by(Hugo_Symbol) %>%
  summarize(N_Other = sum(Mutation_Status == "Other"),
            N_Mutant = sum(Mutation_Status == "Mutant"))

# Merge test results back into full dataset, which restores information lost in the summarization
shrna_data <- merge(shrna_muts_summ, shrna_muts, by = "Hugo_Symbol")

# Add Color column
shrna_data$Color <- ifelse(shrna_data$Mutation_Status == "Other", "cyan3", "darkorchid")
shrna_data$Color <- factor(shrna_data$Color)

# Cell line lineages
shrna_data <- merge(shrna_data, ccl_converter, by = c("CCLE_Name", "Broad_ID"), all.x = TRUE)
levels(shrna_data$lineage_name) <- sort(levels(shrna_data$lineage_name), decreasing = TRUE)

# Copy number
shrna_data <- merge(shrna_data, cn_melt, by = c("Hugo_Symbol", "Broad_ID"), all.x = TRUE)

# Gene expression (RPKM)
ge_filt <- filter(ge_melt, Hugo_Symbol %in% unique(shrna_data$Hugo_Symbol))
shrna_data <- merge(shrna_data, ge_filt, by = c("Hugo_Symbol", "Broad_ID", "CCLE_Name"), all.x = TRUE)

saveRDS(shrna_data, "./../crispr_lineages_giant_files/shrna_data_18Q3.rds", compress = "xz")

shrna_data <- readRDS("./../crispr_lineages_giant_files/shrna_data_18Q3.rds")
shrna_ccl <- data.frame("Broad_ID" = shrna_data$Broad_ID)

10.2 Wilcoxon tests

10.2.1 Grouped by gene

shrna_signif <- compare_means(Score ~ Mutation_Status, group.by = c("Hugo_Symbol"), data = shrna_data, method = "wilcox.test", p.adjust.method = "BH")
shrna_signif <- adj_signif(shrna_signif)
shrna_signif <- shrna_signif[order(shrna_signif$p),]
saveRDS(shrna_signif, "./data_munging/rds/shrna_signif.rds")

shrna_signif <- readRDS("./data_munging/rds/shrna_signif.rds")

knitr::kable(filter(shrna_signif, p < 0.01)[, c("Hugo_Symbol", "p", "p.adj", "p.format", "p.signif", "p.signif.adj")], caption = "shRNA Screen: Wilcoxon Test Results Comparing Mutant and Other Cell Lines, p < 0.1  (Benjamini-Hochberg-corrected p-values: * p <= 0.05, ** p <= 0.01, *** p <= 0.001, **** p <= 0.0001)") %>% kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>% scroll_box(width = "900px", height = "450px")

10.2.2 Grouped by gene and lineage

shrna_signif_lineage <- compare_means(Score ~ Mutation_Status, group.by = c("Hugo_Symbol", "lineage_name"), data = shrna_data, method = "wilcox.test", p.adjust.method = "BH")
shrna_signif_lineage <- adj_signif(shrna_signif_lineage)
shrna_signif_lineage <- mutate(shrna_signif_lineage, lineage_name = reorder(lineage_name, p.adj, mean))
saveRDS(shrna_signif_lineage, "./../crispr_lineages_giant_files/shrna_signif_lineage.rds")

shrna_signif_lineage <- readRDS("./../crispr_lineages_giant_files/shrna_signif_lineage.rds")

11 References

---

Barretina, J., Caponigro, G., Stransky, N., Venkatesan, K., Margolin, A. A., Kim, S., … Garraway, L. A. (2012). The Cancer Cell Line Encyclopedia enables predictive modelling of anticancer drug sensitivity. Nature, 483(7391), 603–607. https://doi.org/10.1038/nature11003

Broad Institute Cancer Dependency Map; Cancer Data Science (2018): Cancer Dependency Map, CRISPR Avana dataset 18Q3 (Avana_public_18Q3). figshare. Fileset. doi:10.6084/m9.figshare.6931364.v1

Consortium, T. C. C. L. E., & Consortium, T. G. of D. S. in C. (2015). Pharmacogenomic agreement between two cancer cell line data sets. Nature, 528(7580), 84–87. https://doi.org/10.1038/nature15736

Data Science, Cancer (2018): DEMETER2 data. figshare. Fileset. doi:10.6084/m9.figshare.6025238.v2

Doench, J. G., Fusi, N., Sullender, M., Hegde, M., Vaimberg, E. W., Donovan, K. F., … Root, D. E. (2016). Optimized sgRNA design to maximize activity and minimize off-target effects of CRISPR-Cas9. Nature Biotechnology, 34(2), 184–191. https://doi.org/10.1038/nbt.3437

Meyers, R. M., Bryan, J. G., McFarland, J. M., Weir, B. A., Sizemore, A. E., Xu, H., … Tsherniak, A. (2017). Computational correction of copy-number effect improves specificity of CRISPR-Cas9 essentiality screens in cancer cells. Nature Genetics, 49(12), 1779–1784. https://doi.org/10.1038/ng.3984

McFarland, J. M., Ho, Z. V., Kugener, G., Dempster, J. M., Montgomery, P. G., Bryan, J. G., … Tsherniak, A. (2018). Improved estimation of cancer dependencies from large-scale RNAi screens using model-based normalization and data integration. https://doi.org/10.1101/305656

12 Session information

---

print(sessionInfo())

## R version 3.5.0 (2018-04-23)
## Platform: x86_64-apple-darwin15.6.0 (64-bit)
## Running under: macOS High Sierra 10.13.6
## 
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/3.5/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/3.5/Resources/lib/libRlapack.dylib
## 
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
## 
## attached base packages:
## [1] grid      parallel  stats     graphics  grDevices utils     datasets 
## [8] methods   base     
## 
## other attached packages:
##  [1] bindrcpp_0.2.2        circlize_0.4.4        ComplexHeatmap_1.18.1
##  [4] bsselectR_0.1.0       caret_6.0-80          lattice_0.20-35      
##  [7] reshape2_1.4.3        devtools_1.13.6       glmnet_2.0-16        
## [10] foreach_1.4.4         Matrix_1.2-14         broom_0.5.0          
## [13] gridExtra_2.3         kableExtra_0.9.0      matrixStats_0.54.0   
## [16] forcats_0.3.0         stringr_1.3.1         dplyr_0.7.6          
## [19] purrr_0.2.5           readr_1.1.1           tidyr_0.8.1          
## [22] tibble_1.4.2          tidyverse_1.2.1       plyr_1.8.4           
## [25] CePa_0.6              data.table_1.11.4     rowr_1.1.3           
## [28] ggsignif_0.4.0        ggpubr_0.1.7.999      magrittr_1.5         
## [31] ggplot2_3.0.0         NMF_0.21.0            Biobase_2.40.0       
## [34] BiocGenerics_0.26.0   cluster_2.0.7-1       rngtools_1.3.1       
## [37] pkgmaker_0.27         registry_0.5         
## 
## loaded via a namespace (and not attached):
##  [1] colorspace_1.3-2    rjson_0.2.20        class_7.3-14       
##  [4] rprojroot_1.3-2     GlobalOptions_0.1.0 pls_2.6-0          
##  [7] rstudioapi_0.7      DRR_0.0.3           prodlim_2018.04.18 
## [10] lubridate_1.7.4     xml2_1.2.0          splines_3.5.0      
## [13] codetools_0.2-15    doParallel_1.0.11   robustbase_0.93-1.1
## [16] knitr_1.20          RcppRoll_0.3.0      jsonlite_1.5       
## [19] gridBase_0.4-7      ddalpha_1.3.4       kernlab_0.9-26     
## [22] sfsmisc_1.1-2       graph_1.58.0        compiler_3.5.0     
## [25] httr_1.3.1          backports_1.1.2     assertthat_0.2.0   
## [28] lazyeval_0.2.1      cli_1.0.0           htmltools_0.3.6    
## [31] tools_3.5.0         igraph_1.2.1        gtable_0.2.0       
## [34] glue_1.3.0          Rcpp_0.12.18        cellranger_1.1.0   
## [37] nlme_3.1-137        iterators_1.0.10    timeDate_3043.102  
## [40] gower_0.1.2         rvest_0.3.2         DEoptimR_1.0-8     
## [43] MASS_7.3-50         scales_0.5.0        ipred_0.9-6        
## [46] hms_0.4.2           RColorBrewer_1.1-2  yaml_2.1.19        
## [49] memoise_1.1.0       rpart_4.1-13        stringi_1.2.4      
## [52] highr_0.7           bibtex_0.4.2        shape_1.4.4        
## [55] lava_1.6.2          geometry_0.3-6      rlang_0.2.1        
## [58] pkgconfig_2.0.1     evaluate_0.11       bindr_0.1.1        
## [61] labeling_0.3        htmlwidgets_1.2     recipes_0.1.3      
## [64] CVST_0.2-2          tidyselect_0.2.4    R6_2.2.2           
## [67] dimRed_0.1.0        pillar_1.3.0        haven_1.1.2        
## [70] withr_2.1.2         nnet_7.3-12         survival_2.42-6    
## [73] abind_1.4-5         modelr_0.1.2        crayon_1.3.4       
## [76] rmarkdown_1.10      GetoptLong_0.1.7    readxl_1.1.0       
## [79] Rgraphviz_2.24.0    ModelMetrics_1.1.0  digest_0.6.15      
## [82] xtable_1.8-2        stats4_3.5.0        munsell_0.5.0      
## [85] viridisLite_0.3.0   magic_1.5-8